Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds significant behavioral context beyond the annotations (which only indicate destructiveHint). It explains the preview behavior ('Set preview=false to apply'), authentication requirements ('Requires authentication (bot password)'), and return details (revision ID, diff URL, undo instructions), providing a thorough understanding of tool behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized into clear sections (BEST for, USE WHEN, NOT FOR, PARAMETERS, RETURNS, NOTE) with front-loaded key information. Each sentence serves a purpose without redundancy, achieving high conciseness while covering essential details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, destructive action, authentication need), the description covers preview behavior, authentication, return values, and examples. However, it omits explicit mention of the 'rationale' parameter, which is a required input. The existence of an output schema is implied but not explicitly described, leaving a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, but the description adds value by providing concrete examples for the 'format' parameter (e.g., 'bold: \'\'\'text\'\'\''), clarifying default behavior for 'all' and 'preview', and detailing 'preview' and 'summary'. However, the 'rationale' parameter is not explicitly discussed in the description, slightly limiting completeness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'BEST for adding formatting markup to specific text,' providing a specific verb and resource. It lists concrete examples of user requests (e.g., 'strike out X') and distinguishes from sibling tool mediawiki_find_replace, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool with a 'USE WHEN' section and provides specific examples. It also includes a 'NOT FOR' section that identifies an alternative tool (mediawiki_find_replace) for replacing text, offering clear guidance on when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnlyHint, idempotentHint, openWorldHint), the description warns that the 'external' check is slow, and states default checks exclude 'external'. This adds valuable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with clear sections (USE WHEN, PARAMETERS, RETURNS), uses bullet points for checks, and is concise with no superfluous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Most aspects are covered: when to use, what checks do, return format. However, it omits explanation of optional input parameters (rationale, pages, category) and how the health score is derived, though output schema may cover return format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds meaning by listing check values with descriptions and providing default/limits for 'limit' parameter. It does not repeat schema details for optional parameters like 'rationale' or 'pages'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Run comprehensive wiki health audit with multiple checks' and enumerates specific check types (links, terminology, orphans, activity, external). It returns a health score and recommendations, distinguishing it from sibling tools that focus on single checks (e.g., mediawiki_check_links).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'USE WHEN' trigger phrases are provided (e.g., 'run health check', 'audit the wiki'). It lists check options, implying when to use which, but does not explicitly state when NOT to use this tool in favor of a more specific sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds value by explaining that missing pages are reported (not errors) and the format option. This clarifies non-error behavior beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with clear sections: main purpose, USE WHEN, NOT FOR, PARAMETERS, RETURNS. Each section is concise and informative, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and the presence of an output schema, the description covers all essential aspects: when to use, parameter constraints, and return behavior (e.g., missing pages reported). It is fully adequate for an agent to use effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with descriptions. The description restates parameter purposes (titles for page list, format for output) and mentions max 50, matching schema. Since schema does the heavy lifting, a baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves content from multiple pages. It distinguishes from siblings by mentioning speed advantage over individual calls and explicitly excludes single-page use (mediawiki_get_page) and metadata-only use (mediawiki_batch_get_pages_info).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'USE WHEN' and 'NOT FOR' sections provide clear guidance. 'USE WHEN: You need content from 2+ pages.' 'NOT FOR: Single page (use mediawiki_get_page). Not for metadata only (use mediawiki_batch_get_pages_info).' This effectively steers the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and idempotentHint annotations, the description specifies return details (metadata per page, exists=false for missing) and a max of 50 titles.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections (purpose, when/not for, parameters, returns). Each sentence provides value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With annotations, output schema, and clear sibling distinctions, the description fully covers usage, parameters, and return behavior for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions; the description adds the max 50 limit for titles, which is not in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get metadata for MULTIPLE pages' and explicitly distinguishes from siblings: 'mediawiki_get_page_info' for single page and 'mediawiki_batch_get_pages' for content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit USE WHEN and NOT FOR conditions, directly naming alternative tools for single pages or content retrieval.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide destructiveHint=true; description adds crucial details like 'ALWAYS use preview=true first' and authentication requirements, enhancing transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with logical sections: purpose, usage, parameters, warning, return info, note; every sentence adds value and no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex destructive tool, the description covers all necessary aspects: purpose, usage context, parameter details, safety warning, authentication, and return info.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds practical advice (e.g., 'ALWAYS use true first!' for preview, explanation of regex escaping) that goes beyond schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Update text across MULTIPLE pages at once' with a specific verb and resource, and distinguishes from the sibling mediawiki_find_replace tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'USE WHEN' and 'NOT FOR' sections, with clear alternatives mentioned (mediawiki_find_replace for single pages).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld. Description adds that it performs HTTP requests and returns status codes, response times, and broken link identification. Could mention potential rate limits or external dependency, but overall good.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise, well-structured with sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS). Every sentence adds value, no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a simple tool, good annotations, and output schema, the description covers purpose, usage, parameters, and return value. No critical gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds little beyond schema: repeats parameter info (urls max 20, timeout default 10) but provides no new semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'verify' and resource 'external URL accessibility', with explicit usage examples. It distinguishes from sibling tool mediawiki_find_broken_internal_links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Includes explicit 'USE WHEN' and 'NOT FOR' sections, providing clear context for when to use and an alternative tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable detail about return values (violations with page, line, wrong term, correct term) and explains the exclude_code_blocks parameter's purpose to avoid false positives, enhancing transparency beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: one sentence for purpose, a USE WHEN line, parameter list, and returns. Every sentence is informative with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and full schema coverage, the description is complete. It covers purpose, usage, parameters, and output. A small gap is the lack of when-not-to-use guidance, but the annotations and schema fill the rest.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, baseline is 3. The description adds meaning by explaining exclude_code_blocks as avoiding false positives on code paths, which is not evident from the param name alone. This adds value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb+resource: 'Scan pages for terminology violations against a glossary.' This clearly distinguishes it from sibling tools like mediawiki_check_links or mediawiki_check_translations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes an explicit 'USE WHEN' section with example user queries, providing clear context. However, it does not mention when not to use or suggest alternatives, but the examples sufficiently guide typical usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds that it returns missing translations grouped by language, which is useful but not extensive. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections for purpose, usage, parameters, and returns. It is concise with no redundant information, using front-loaded key details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters and a clear use case, the description covers usage scenarios and return format adequately. However, it does not elaborate on pattern options or handle the minor inconsistency in limit default (50 vs 20).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description provides a concise summary and examples for parameters like languages and pattern, adding marginal value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds pages missing translations, with specific verbs 'find' and resource 'pages missing translations'. It distinguishes itself from sibling tools like mediawiki_check_terminology by focusing on translation gaps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'USE WHEN' section provides explicit examples of user queries that trigger this tool, such as 'which pages need German translation'. It offers clear context but does not mention when not to use it or explicitly contrast with alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds that the tool returns an HTML-formatted diff with colored additions/deletions, providing useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, well-structured with clear headings (USE WHEN, NOT FOR, PARAMETERS, RETURNS), and front-loads essential information in two sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, full schema coverage, and presence of output schema and annotations, the description covers all necessary aspects: usage context, parameter roles, return type, and exclusions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). The description groups parameters with 'OR' logic and clarifies that from_title/to_title use the latest revision, adding meaning beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Compare two revisions and show the diff' and distinguishes from siblings like mediawiki_get_revisions (for listing) and mediawiki_compare_topic (for comparing across pages).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly states 'USE WHEN' scenarios and 'NOT FOR' cases with specific alternative tool names (mediawiki_get_revisions, mediawiki_compare_topic).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, and open-world hints. Description adds what the tool returns (page mentions with context, mismatches, inconsistencies), providing behavioral context beyond annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise, well-structured with headers (USE WHEN, NOT FOR, PARAMETERS, RETURNS). Every sentence adds value, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given tool complexity (topic comparison across pages) and existence of output schema (referenced in RETURNS), description covers usage, parameters, and return values completely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description repeats param info but adds default value for limit and clarifies purpose of category. Adds little beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description opens with clear verb + resource: 'Compare how a topic is described across multiple pages.' It explicitly distinguishes from sibling tool mediawiki_compare_revisions in NOT FOR section.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Has explicit USE WHEN and NOT FOR sections that state when to use and when not to, with a named alternative tool (mediawiki_compare_revisions).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, so the description doesn't need to restate safety. It adds context on themes and options (e.g., add_css, reverse_changelog), which is helpful but not critical beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (WHEN TO USE, THEMES, OPTIONS, EXAMPLE). Each sentence adds value, no redundancy, and the critical info is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description does not need to detail return values. It covers purpose, usage guidelines, options, and an example, leaving no gaps for a conversion tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining theme options with examples and the example output, which enhances understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it converts Markdown to MediaWiki markup, using a specific verb and resource. It distinguishes itself from siblings like mediawiki_edit_page and mediawiki_parse by focusing solely on format transformation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'WHEN TO USE' section provides explicit scenarios (e.g., converting GitHub docs, README files). However, it does not mention when not to use the tool or suggest alternative siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Expands on annotations (destructiveHint) with warning about overwriting entire content. Discloses authorization needs (bot password) and return value contents (revision ID, diff URL, undo instructions). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with labeled sections. Core action stated first. Every sentence is informative and non-redundant. Efficient use of space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given complexity (mutation tool with 9 params, destructive, auth required), description covers all critical aspects: purpose, usage conditions, behavioral warnings, parameter hints, return info, and constraints. Output schema exists, so return details are sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). Description adds practical hints for parameters like 'summary: required for good practice' and emphasizes that section must be specified to avoid overwrite, but does not cover all 9 params (e.g., rationale, captcha). Still adds meaningful context above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb+resource: 'Create new pages or rewrite entire page content.' Distinguishes from siblings with explicit 'NOT FOR' section naming alternatives like mediawiki_find_replace and mediawiki_apply_formatting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'USE WHEN' and 'NOT FOR' sections provide clear context and exclude alternatives. Mentions authentication requirement for anonymous restrictions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. Description adds scanning behavior (pages/category/limit) and return details (broken links with source, line, context), which is useful but does not significantly extend beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with clear sections (purpose, usage, parameters, returns), concise without waste. Front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given annotations and output schema, the description covers purpose, usage, parameters, and returns adequately. Minor gaps: edge cases (e.g., both pages and category specified) not addressed, but overall complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds moderate value by rephrasing parameter purpose and default values, but misses the max 100 constraint mentioned in schema. Does not significantly improve understanding beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it finds internal wiki links pointing to non-existent pages, using specific verb+resource. Distinguishes from sibling tools like mediawiki_check_links by focusing on internal dead links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'USE WHEN' and 'NOT FOR' sections, and names the alternative tool for external URLs. This gives the agent clear guidance on when to invoke this tool vs. siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description carries less burden. It adds that the tool returns a 'List of orphaned page titles', which is useful but not extensive behavioral detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured with clear sections (USE WHEN, PARAMETERS, RETURNS). Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists, the description adequately covers purpose, usage cues, and parameter details. It lacks mention of maximum limit (schema says max 200) but is otherwise complete for a simple read-only tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers all parameters with descriptions (100% coverage). The description repeats parameter info but adds minor context (e.g., default namespace 0, limit default 50). Baseline 3 is appropriate as it does not significantly extend schema meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool's function: 'Find pages with no incoming links from other pages'. This is a specific verb+resource combination that clearly distinguishes it from sibling tools like mediawiki_get_backlinks (which finds backlinks for given pages) and mediawiki_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a 'USE WHEN' section with example user queries ('find orphan pages', 'which pages have no links'), which guides the agent on appropriate invocation context. However, it does not explicitly mention when not to use it or compare to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes beyond annotations (destructiveHint=true) by detailing authentication requirements, preview default for safety, return values including match count, revision ID, diff URL, and undo instructions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS, NOTE), front-loaded purpose, and no unnecessary words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all aspects: usage, parameters, return values, authentication, and safety. The description is fully self-contained for an agent to use correctly, especially given the tool's complexity and sibling count.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While schema coverage is 100% (baseline 3), the description adds practical context like 'preview: default true for safety' and regex caveats, enhancing understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it's for simple text changes on a single page, uses specific verbs like 'replace', 'fix', 'change', 'update', and distinguishes from sibling tools like mediawiki_edit_page and mediawiki_bulk_replace.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides 'USE WHEN' and 'NOT FOR' sections with concrete examples and alternative tools, giving clear guidance on when to use this tool vs others.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, so the description adds value by describing the return content (similarity scores, linking recommendations). It does not conflict with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the main purpose, uses clear sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS), and every sentence is necessary. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, usage guidance, all parameters, and return value. With output schema available, it provides enough context for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are well-documented in the schema. The description restates parameter info (e.g., min_score range, limit defaults) without adding significant new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'find' and resource 'pages with similar content', and explicitly calls out 'potential duplicates or overlaps'. It distinguishes from sibling tools like 'mediawiki_get_related' which finds related pages by links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'USE WHEN' and 'NOT FOR' sections guide when to use the tool and name the alternative tool 'mediawiki_get_related', providing clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds that it returns a list of pages and notes parameter defaults (limit 50, include_redirects false), providing useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured into clear sections: one-line purpose, USE WHEN/NOT FOR, PARAMETERS, RETURNS. It is concise with no wasted words, front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a simple tool with 5 parameters (including rationale), output schema existence, and clear return description ('List of pages'), the description is complete. It also distinguishes from a relevant sibling, covering all necessary context for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds default values for limit (50) and include_redirects (false) not fully covered in schema, and clarifies optionality of parameters, adding value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Get pages that link TO a specific page ("What links here")' which is a clear verb+resource. It distinguishes from sibling mediawiki_get_external_links by explicitly stating it is not for outgoing external links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides 'USE WHEN' examples (e.g., 'what links to X') and 'NOT FOR' excluding outgoing links with an explicit alternative tool. This gives clear guidance for when to select this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, covering the safety profile. The description adds no additional behavioral details, but does not contradict annotations. With annotations present, a score of 3 is appropriate as the description adds marginal value beyond the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with clear sections (purpose, usage, parameters, returns). Every sentence is informative with no wasted words. The structure is well-organized and front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has a moderate parameter count (5, 1 required), 100% schema coverage, annotations, and an output schema (mentioned in context), the description is complete. It covers purpose, usage, parameters, and return value, leaving no gaps for an agent to understand how to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the baseline is 3. However, the description section provides additional context for each parameter (e.g., 'Category name without "Category:" prefix') that adds meaning beyond the schema's descriptions (which say 'with or without'), earning a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get all pages that belong to a specific category' and distinguishes from the sibling tool 'mediawiki_list_categories' by explicitly stating 'NOT FOR: Listing categories themselves (use mediawiki_list_categories).' This provides a specific verb and resource with clear differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'USE WHEN' examples and a 'NOT FOR' clause naming the alternative tool, giving clear guidance on when to use this tool vs. alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, indicating a safe, idempotent read operation. The description adds that it returns a list of external URLs and mentions the required parameter, providing sufficient behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections, front-loaded main purpose, and no wasted words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and comprehensive annotations, the description is complete. It covers the required parameter and return type, and the tool is simple enough that no further context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is 3. The description adds a bit more context ('Page name (required)') beyond the schema's 'Page title to get external links from', but not significantly enough to justify a higher score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it gets all external URLs from a wiki page, using specific verbs and resources. It distinguishes from sibling tools like mediawiki_get_backlinks and mediawiki_check_links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'USE WHEN' and 'NOT FOR' sections, with clear guidance on when to use this tool and alternatives, such as mediawiki_get_backlinks for incoming wiki links and mediawiki_check_links for verifying links.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, and open-world behavior. The description adds the batch size limit (max 10) and the return format (grouped by source page), providing useful extra context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured with clear sections: purpose, when to use, limitations, parameters, and returns. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a simple batch retrieval tool given the annotations and output schema. It could mention behavior for missing pages, but that is a minor omission.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description repeats the information already in the schema (titles is a required array of strings, max 10). No additional parameter meaning is provided beyond what the schema offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is for batch retrieval of external URLs from multiple pages, and explicitly distinguishes from the single-page sibling tool mediawiki_get_external_links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It includes explicit USE WHEN and NOT FOR sections, providing examples of user intents and directing to an alternative for single-page requests.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly=true, idempotent=true, openWorldHint=true. Description adds valuable context about return types (titles, URLs, dimensions, file sizes), fully aligning with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Structured into USE WHEN, PARAMETERS, and RETURNS sections. Every sentence adds value. Concise and well-organized for agent consumption.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With output schema present and schema coverage 100%, description adds return type details. Sufficient for a straightforward read-only tool with 3 parameters. No gaps identified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all parameters with descriptions (100% coverage). Description restates 'title: Page name (required)' and 'limit: Max images (default 50)', but the schema already includes defaults and constraints. No additional semantic value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Get all images and files used on a wiki page.' with specific verb and resource. Usage cues further clarify scope. Distinguishes from sibling tools that handle pages, revisions, categories, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'USE WHEN' section provides clear context for agent to select tool. No explicit 'when not to use' or alternatives listed, but the description is sufficient given sibling diversity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and idempotent behavior. The description adds important behavioral detail: large pages are truncated at 25KB. This goes beyond what annotations provide, though no additional info on auth or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a single-line purpose, then USE WHEN, NOT FOR, and parameter list. Every sentence is necessary and adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (many siblings, output schema exists), the description covers purpose, usage, parameter details, truncation behavior, and fallback advice. It is complete for an agent to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with descriptions for all three parameters. The description adds minimal extra semantics (e.g., default format 'wikitext'), but mostly restates schema info. Baseline of 3 is appropriate as schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Retrieve full wiki page content' with a specific verb and resource. It explicitly distinguishes from sibling tools like mediawiki_get_sections, mediawiki_search_in_page, and mediawiki_get_page_info by stating what it is NOT for.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit USE WHEN examples and NOT FOR conditions with alternative tool names. Also advises to use mediawiki_resolve_title if title is not found, offering full guidance on when to use this tool vs alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable specifics about what metadata is returned (last edit timestamp, page size, protection status, creator), going beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Highly concise with structured sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS). Front-loaded with purpose. Every sentence adds value with zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, usage guidance, parameters, and return values. With annotations and output schema present, the description provides sufficient context for correct tool selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters described. The description repeats 'title: Page name (required)' which adds no new meaning over the schema's 'Page title'. The optional 'rationale' parameter is not mentioned, but it's self-explanatory. Minimal value added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get page metadata without content', uses specific verbs and resources, and distinguishes from siblings mediawiki_get_page (content) and mediawiki_get_revisions (edit history). Lists concrete use-case examples.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Includes explicit 'USE WHEN' with example queries and 'NOT FOR' sections naming alternative tools. Provides clear decision criteria for when to use this tool vs siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. Description adds context: returns lead section, page size, categories, section list, last edit timestamp, and mentions lighter weight for large pages. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections, bold headings, and front-loaded key info. Each sentence adds value. Minor redundancy ('much lighter' could be merged), but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists and annotations are present, the description provides comprehensive context: purpose, usage guidelines, return values, and sibling relationships. No gaps for this tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (both rationale and title described in detail). Description adds minimal parameter info beyond schema, simply restating that title is required. With high schema coverage, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it gets the lead section and key metadata, distinguishing from full page retrieval and section access. It uses specific verb 'Get' and resource 'page summary'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('What is X about', 'quick overview') and when not to, with direct references to sibling tools (mediawiki_get_page for full content, mediawiki_get_sections for specific sections).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds behavioral context: default limit, aggregation behavior, and response summary. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (main, USE WHEN, NOT FOR, PARAMETERS, RETURNS). It is concise, front-loaded, and every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description appropriately summarizes return values. It covers purpose, usage, parameters, and output, leaving no important gaps given the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good descriptions. The description adds a PARAMETERS section summarizing key parameters, but adds limited new detail beyond the schema. Still, it helps by grouping and clarifying aggregation behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Get recent changes across the entire wiki', specifying a clear verb and resource. It lists use-case examples and explicitly distinguishes from siblings like mediawiki_get_revisions and mediawiki_get_user_contributions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes 'USE WHEN' and 'NOT FOR' sections with explicit alternative tool names, providing unambiguous guidance on when to use this tool instead of others.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds that it returns related page titles with relationship type, which is consistent and confirms behavioral traits. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with clear sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS). It is concise, front-loaded, and every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description covers usage context, parameters, and return summary. It is sufficient for the tool's complexity, though no examples are provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents all parameters. The description repeats defaults and enumeration but adds no new meaning beyond summarizing. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Find pages related to a given page via links and categories' with specific verb+resource. It distinguishes from sibling tool mediawiki_find_similar_pages, which is for duplicate detection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit USE WHEN and NOT FOR sections provide clear context for when to call this tool, including example user queries, and explicitly state when not to use it, pointing to an alternative sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, idempotentHint, and openWorldHint. The description adds that it returns a revision list with timestamps, users, sizes, and edit summaries, which is valuable behavioral context beyond annotations. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS) and is front-loaded. However, the inaccuracy about the limit default and omission of a parameter prevent a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 6 parameters and existence of an output schema, the description covers the core purpose, usage guidelines, and return format. However, the inaccuracy about limit default and missing rationale parameter, along with no mention of openWorldHint implications, leave gaps for a comprehensive understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description contains an inaccuracy: it states default limit is 50, while the schema says default 20. It also omits the 'rationale' parameter. This misleads the agent, reducing the score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get revision history for a specific page' with a specific verb and resource. It explicitly distinguishes from siblings by stating what it is not for and naming alternatives (mediawiki_get_recent_changes, mediawiki_compare_revisions).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit use cases ('who edited the FAQ', 'show edit history of X') and when not to use it ('Wiki-wide activity', 'comparing versions'), with direct references to alternative tools. This fully guides the agent on proper invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds behavioral context: omitting section returns TOC, section=0 is intro, format options (wikitext/html), and the nature of the return value. This supplements the annotations well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is divided into clear sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS). Every sentence adds value, no redundancy. It's concise yet comprehensive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description does not need to detail return values. It covers all necessary aspects: purpose, usage scenarios, parameter behavior, and differentiation from siblings. No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds significant usage context: explains conditional behavior (omit section for TOC, section=0 for intro, default format). This goes beyond the schema descriptions and helps the agent understand parameter interactions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool retrieves page section structure (TOC) or specific section content. It uses specific verbs like 'get' and 'retrieve' and distinguishes from the sibling tool 'mediawiki_get_page' which handles full page content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit use cases are provided: 'User asks what sections does X have, show table of contents, get the Installation section'. It also explicitly states what NOT to use it for and directs to the appropriate alternative, which is excellent guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint, idempotentHint, openWorldHint. The description adds that results are sorted by last edit (oldest first) with days since edit and last editor, enhancing transparency without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured with clear sections: one-sentence purpose, 'USE WHEN', 'NOT FOR', 'PARAMETERS', 'RETURNS'. No extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, full schema coverage, rich annotations, and presence of an output schema, the description fully covers purpose, usage, parameters, and output format. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 5 parameters have schema descriptions, so baseline is 3. The description adds defaults (days: 90, limit: 50) and constraints (max: 200, default namespace 0), adding value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Find pages that haven't been edited in a specified number of days.' It distinguishes from siblings by explicitly listing use cases and alternatives in 'USE WHEN' and 'NOT FOR' sections.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'USE WHEN' examples (e.g., 'find outdated pages') and 'NOT FOR' directives, referencing specific sibling tools like mediawiki_get_recent_changes and mediawiki_find_orphaned_pages.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, openWorldHint, and idempotentHint. The description adds that it returns a list of pages with timestamps and summaries, and mentions default/max limits, which complements annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS), concise without unnecessary words, and front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool is read-only with output schema available, the description covers purpose, usage guidance, parameter details, and return value, making it fully complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description lists parameters with brief explanations (e.g., 'default 50' for limit) but does not add substantial meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Get all edits made by a specific user' with a clear verb-resource combination. It explicitly distinguishes from sibling tools by saying 'NOT FOR: Page-specific history (use mediawiki_get_revisions). Not for wiki-wide activity (use mediawiki_get_recent_changes).'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a dedicated 'USE WHEN' section listing example user queries and a 'NOT FOR' section with explicit alternative tool names, providing excellent guidance on when and when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly and idempotent, so the description adds return value specifics. However, claiming 'PARAMETERS: None' contradicts the schema and misleads about expected inputs, reducing transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise with three lines plus a structured 'USE WHEN' section. No unnecessary verbiage; information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given low complexity (no required params, output schema present), the description covers purpose, usage, and return info. It misses mentioning the optional rationale parameter's purpose, but output schema likely covers details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% but the description says 'PARAMETERS: None', which is incorrect given the rationale parameter. This diminishes rather than adds meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves wiki information and gives specific use cases (wiki statistics, version). However, it inaccurately says 'PARAMETERS: None' while the schema includes an optional rationale parameter, slightly clouding the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'USE WHEN' section explicitly lists user queries that trigger this tool, providing clear guidance on when to use it among many sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide safety hints; description adds return format (category names and page counts) and pagination behavior, exceeding minimal requirement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-organized with sections for usage, parameters, and returns; every sentence adds value and is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, description covers purpose, usage, parameters, and return format adequately for a simple list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and parameter descriptions are already clear; description adds no new information beyond listing parameters with minor redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'List all categories in the wiki' and distinguishes from sibling tool mediawiki_get_category_members.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit USE WHEN and NOT FOR sections with alternative tool named, providing clear context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint and idempotentHint, confirming safe read behavior. The description adds value by explaining pagination via continue_from and stating returns of page titles and IDs, but does not elaborate on rate limits or other side effects beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, well-structured with sections for usage, parameters, and returns. Every sentence serves a purpose without redundancy, and the purpose is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 optional parameters, full schema coverage, and an output schema, the description adequately covers pagination and return format. It could be slightly more explicit about pagination iteration, but overall it provides sufficient context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with all parameters described. The description restates parameter info in a bullet list, adding marginal value with reminders of defaults (e.g., default 50 for limit), but does not introduce new semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List wiki pages' with specific verb and resource, and distinguishes from the sibling tool 'mediawiki_search' by explicitly noting it is not for finding by content. This provides precise purpose differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes explicit 'USE WHEN' and 'NOT FOR' sections, giving concrete examples like 'list all pages' and directing to alternatives for content search. This provides clear guidance on tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds that it returns user names, groups, edit counts, and registration dates, which is useful beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections for USE WHEN, PARAMETERS, and RETURNS. Every sentence provides useful information; no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 5 parameters and presence of output schema, the description fully explains the tool's behavior and return values, leaving no gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. The description adds context like default limit of 50 and that active_only filters for last 30 days, which adds value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists wiki users with optional group filtering, and provides example queries like 'who are the admins'. It is distinct from sibling tools, none of which list users.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly lists use cases (e.g., 'who are the admins', 'list all users') but does not mention when not to use it or provide alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already include destructiveHint, but description adds authentication requirement and preview behavior, though does not detail all edge cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-organized sections (USE WHEN, NOT FOR, PARAMETERS, RETURNS, NOTE) with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all relevant aspects: purpose, parameters, return values, authentication requirements, and conflicts with siblings; output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds clarity (e.g., 'without Category: prefix', default false for preview) and explains the rationale parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Add or remove categories from a page' and distinguishes from listing categories (mediawiki_list_categories) and getting category members (mediawiki_get_category_members).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides USE WHEN examples ('add category X', 'remove from category Y') and NOT FOR exclusions with sibling tool names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses side effect (creates redirect), permissions requirement, and default behaviors. Annotations include destructiveHint=true; description does not contradict and adds context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with a clear purpose, usage guidance, parameter list, return value, and warning. Every section is concise and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all necessary aspects: purpose, usage, parameters, return values, permissions, and side effects. Sufficient for a complex tool with 7 parameters and no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds value by listing parameters with defaults and practical notes (e.g., 'requires suppressredirect right' for no_redirect).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Explicitly states 'Move (rename) a wiki page' with clear verb and resource. Differentiates from siblings in 'NOT FOR' section by naming mediawiki_edit_page and mediawiki_find_replace.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides specific 'USE WHEN' examples and a 'NOT FOR' section with explicit alternatives, giving clear guidance on when to use this tool vs others.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, and open-world. Description adds that the tool returns rendered HTML and explains the 'title' parameter's effect on template expansion, providing useful behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is succinct with clear sections (USE WHEN, PARAMETERS, RETURNS). Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not detail return values. It covers core functionality well, though could mention error handling or limits for completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers all parameters with descriptions (100% coverage). Description adds value by clarifying that 'title' affects link resolution and template expansion, going beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool parses wikitext to HTML. It distinguishes from siblings like 'mediawiki_edit_page' and 'mediawiki_convert_markdown' by specifying the core function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'USE WHEN' section provides explicit use cases (preview rendering, test syntax). While it does not exclude other uses, it offers clear guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.