Writing Style Checker

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

The description elaborates beyond the readOnlyHint annotation: it states the tool is stateless, text is analyzed in memory on the hosted server and never stored, and it returns a detailed plain-text report. It also discloses that the hosted server has no filesystem access and mentions the error condition for large texts. 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 concise at just four sentences. It is front-loaded with the main purpose, then lists specific issues, followed by behavioral details, error handling, and references to related tools. Every sentence serves a clear function 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?

Despite the absence of an output schema, the description fully describes the return format (plain-text report with line/column, matched text, context, and reason for AI tells). It also covers input constraints, behavior (stateless, in-memory), error conditions, and relationships to other tools. Given the tool's moderate complexity, this is comprehensive.

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 already provides 100% coverage for all three parameters. The description adds value by specifying a behavioral constraint on the text parameter (100k character limit causing an error), which is not in the schema. It does not elaborate on config or format beyond what the schema offers, but the added constraint justifies a slightly above-baseline 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 begins by explicitly stating the tool's purpose: analyze text for writing style issues. It lists specific categories of issues (weasel words, passive voice, etc.), clearly distinguishing it from sibling tools like fix_duplicates (for fixing) and check_file (for local files).

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 clear guidance on when to use this tool: it is read-only and stateless, appropriate for analysis only. It mentions that for local files, check_file should be used, and for auto-removing duplicates, fix_duplicates is the follow-up. It also notes a constraint: texts over 100,000 characters return an error.

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 set readOnlyHint=true. The description adds context: 'Read-only with no side effects: the fix is returned in the response, nothing is written anywhere.' This reinforces the read-only nature and explains practical implications. 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?

Two sentences clearly convey purpose, scope, output, safety, and usage context. Every word adds value; no redundant 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 simplicity (one parameter, no output schema), the description adequately explains what the tool does, what it returns (cleaned text + list of removed words), and when to use it. 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 description coverage is 100% for the single parameter 'text'. The description adds behavioral details ('case-insensitive, including across line breaks') that help the agent understand input handling, going beyond the schema's generic 'text to clean'.

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 action: 'Remove duplicate adjacent words' with specific scope (case-insensitive, across line breaks) and output. It also distinguishes from siblings by indicating it is used after check_text reports duplicates, and that other issues are report-only.

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 usage guidance: 'Use after check_text reports duplicate words' and exclusion: 'other issue types are report-only and have no auto-fix.' This clearly tells the agent when to invoke this versus 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 provide readOnlyHint=true. Description adds that it is idempotent ('returns same catalog for a given release') and takes no parameters. 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?

Two sentences, no wasted words. Front-loaded with purpose and return content, followed by usage guidance. Every sentence earns its place.

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 tool with no parameters and no output schema, the description is fully complete. It explains what is returned (lists with counts, keys, samples, link), guarantees idempotence, and gives usage context.

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?

No parameters, schema coverage 100%. Description explicitly states 'takes no parameters', adding clarity beyond the empty schema. Baseline for 0 params is 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 it returns detector word lists with specific details (entry count, config key, sample entries, link). Verb is 'Return', resource is 'detector word/phrase list'. Distinguishes from sibling tools like 'check_text' and 'fix_duplicates'.

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 ('before tuning config for check_text') and when not needed ('not needed for ordinary checking'). Provides clear context for appropriate invocation.

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