library

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

Adds context beyond readOnlyHint: mentions hash-chained changelog, returns a fresh cursor, and up_to_date flag. No contradiction with annotations. Provides useful behavioral details.

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 with dense information and no fluff. First sentence explains core functionality, second offers 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?

With 6 parameters, no output schema, and sparse annotations, the description fails to explain key parameters like limit, offset, and filtering options. Core idea is clear but incomplete for effective usage.

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 0%, so description must compensate. It only partially explains the 'since' parameter (cursor run_id or ISO timestamp) but ignores limit, offset, tier, index, path_prefix. Insufficient for 6 parameters.

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 returns net added/modified/removed pages since a cursor, referencing a hash-chained changelog. It is specific about the resource and action but does not explicitly differentiate from sibling tools like diff_md or snapshot_status.

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?

Implies usage for incremental updates ('Read only what it returns instead of re-reading the corpus') and indicates up_to_date:true means nothing new. However, no explicit when-not-to-use or comparison to alternatives like diff_md or fetch.

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, but the description adds valuable behavioral context: it returns only 'changed hunks + both content_hashes', not a full page. It also steers the agent to pair with changed_since for page-level changes. 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?

Two sentences, zero waste. Front-loaded with the core action and resource. 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 no output schema and 5 parameters (3 required), the description covers the essential usage and return format. It lacks details on 'path' and 'index' but the purpose and parameter hints are sufficient for an AI agent. Could be improved by noting that 'path' is the page path. Overall, it is mostly 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 0%, so the description must compensate. It explains 'from' as a run_id or ISO timestamp, and 'to' defaults to current. It implies 'context' via 'unified diff' (common parameter). However, it does not explain 'path' or 'index' beyond their names, leaving some ambiguity. Still, the key parameters are well-described.

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 computes a unified diff for ONE page between two snapshots. It specifies the 'from' parameter requirement and defaults for 'to'. It distinguishes from sibling 'changed_since' by noting it returns changed hunks and content hashes for a single page, not just a list of changed 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?

Explicit guidance: 'from=<run_id|ISO ts> required; to defaults to current' and 'pair with changed_since for which pages moved'. This tells the agent when to use this tool (diff one page) versus the sibling (list changed 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 readOnlyHint=true. The description adds value by detailing the return structure (full text + metadata receipt with content_hash, fetched_at, run_id) and mentions the upgrade to a verifiable proof via prove(url), which goes beyond the 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 with two sentences. It front-loads the core action and return value in the first sentence, and adds an optional upgrade feature in the second without any 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?

For a simple read-only tool with one parameter and no output schema, the description covers purpose, parameter format, return value, and a related tool (prove). It is sufficiently complete for an agent to select and invoke 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?

The input schema has 0% description coverage for the parameter 'id'. The description compensates by specifying the expected format ('<index>:<path>'), adding meaning beyond the schema's type and length constraints. However, it does not elaborate on what index or path refer to.

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 'Fetch' and the resource 'one document by search id', specifying the id format as '<index>:<path>'. However, it does not explicitly distinguish this tool from siblings like 'read_md' or 'search', which also fetch documents, lacking explicit 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 no guidance on when to use this tool versus alternatives. It does not mention when not to use it or suggest which sibling tools are better suited for different scenarios.

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?

The description adds value beyond annotations by disclosing pagination behavior (cursor-paginated, 500 paths/page). However, it does not mention other behavioral traits like rate limits, authentication requirements, or that it is read-only (already covered by readOnlyHint). Annotations already provide read-only safety, so the description's addition is useful but not extensive.

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 short and front-loaded with the core concept (fnmatch glob). However, it is perhaps too concise, omitting important details. It earns a 4 because it is not verbose but still lacks completeness.

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 4 parameters, no output schema, and medium complexity, the description is insufficient. It does not explain return values (list of paths?), cursor usage, or error behavior. An agent would need to infer too much from the example.

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 0%, and the description only provides an example pattern but does not explain any parameters (index, cursor, max_results). It fails to add meaning beyond the raw schema, which lists names and types. The default value for max_results (500) is not mentioned.

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 indicates it is a glob tool for matching file paths, with an example pattern and pagination info. It distinguishes it from sibling tools like grep_corpus (file content search) and list_dir (listing a directory). However, it could be more explicit about its function (e.g., 'list file paths matching a pattern').

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 does not provide guidance on when to use this tool versus alternatives. It lacks comparisons with siblings like search or list_dir, and does not mention prerequisite knowledge (e.g., understanding of fnmatch syntax).

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 declare readOnlyHint=true, so the agent knows it's a read operation. The description adds that it runs regex over current/md, files_only skips snippets, caps hits at 200, and can error with INVALID_PATH/TIMEOUT. This provides useful behavioral context beyond the annotation.

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 short (one sentence plus fragments), front-loading the core function. Every phrase adds value. Could be more structured but is 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?

With 7 parameters, no output schema, and complex behavior (regex, path, case, context, bounds), the description is too sparse. It omits many parameter semantics and output format. Even with readOnly annotation, it is incomplete for full agent 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 description coverage is 0%, so the description must explain parameters. It only explains files_only's effect and implies the path default. It does not explain pattern, ignore_case, context, index, or max_matches behavior. The cap mention aligns with max_matches but is ambiguous (default 200, max 500). Inadequate for 7 parameters.

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 performs regex search over markdown files (current/md). It specifies the behavior of files_only, a hit cap of 200, and possible errors. The name 'grep_corpus' reinforces this. Among siblings like 'search' and 'glob_corpus', this is distinct as a regex-based search on md 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?

No guidance on when to use this tool versus its siblings. It does not compare with 'search', 'glob_corpus', or other tools. The description only gives constraints but no decision context for 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?

Description adds behavioral context beyond annotations: limit of 500 results and the fact that only immediate children are returned. Annotations already indicate read-only and deterministic behavior, but the description enriches with operational 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?

Extremely concise and front-loaded. The single sentence conveys core functionality and output details. However, the structure lacks any mention of the 'index' parameter, which slightly detracts from completeness.

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 simple tool with no output schema, the description covers return fields and limit but omits explanation of the optional 'index' parameter. Given the simplicity, it is mostly complete but leaves a notable gap for agents.

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 0% schema description coverage, the description must compensate but only partially covers 'path' by implying it's a directory. The 'index' parameter is entirely ignored, leaving its purpose unclear.

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 explicitly states that the tool lists immediate children of a directory, returning name, kind, and size with a limit of 500. It clearly distinguishes from sibling tools like glob_corpus or search, which serve different purposes.

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?

No guidance on when to use this tool vs. alternatives. The description does not mention prerequisites or scenarios where other sibling tools should be preferred, leaving the agent to infer from names alone.

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, so the description's behavioral context is limited to listing fields. The description adds value by specifying output fields and the relationship to other tools, but does not disclose additional behaviors 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 two sentences with no redundancy, front-loading the purpose and providing useful context in the second sentence.

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 no parameters, no output schema, and annotations are present, the description adequately explains the output fields and their relevance to other tools. It is succinct and 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?

The tool has no parameters, and the schema coverage is 100%. Per guidelines, baseline for 0 params is 4. The description does not add parameter information as there are none.

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 (list implied) and resource (library catalog/indexes) and lists specific fields returned. It distinguishes from sibling tools that perform other operations (e.g., fetching, searching, diffing).

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 mentions that other tools take an optional index parameter using the slug from this tool, providing context for using the output. It does not explicitly state when not to use this tool, but the purpose is clear.

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 declare readOnlyHint=true, already indicating no side effects. The description adds that a false inclusion result is not an error, which is behavioral context beyond annotations. Offline verification command is shared.

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 efficiently cover purpose, usage, and a notable behavior. 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?

Description provides essential context for a verification tool: what it proves, how to specify history, and how to verify offline. Lacks details on error handling, but with readOnlyHint and no output schema, it is reasonably 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?

With 0% schema coverage, the description adds meaning for url (implicitly) and as_of (explicitly via <run_id|ISO ts>). However, the index parameter is not explained, leaving a gap.

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 provides a Merkle inclusion proof for a URL's content_hash committed by a snapshot root. It distinguishes from sibling tools like fetch or search by focusing on verification of commitment.

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 explains the as_of parameter for historical proofs and clarifies that included:false is not an error, guiding correct interpretation. However, it does not explicitly compare with alternatives or state 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?

Discloses read-only behavior (consistent with readOnlyHint=true), format savings (~40% bytes), cursor pagination, and page limit. Adds value 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?

Three concise sentences, front-loaded with purpose and key details. 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?

Covers main aspects (read-only, performance, pagination) but misses SQL syntax constraints, index parameter purpose, and return format. Adequate but not thorough.

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 0% schema coverage, description partially compensates: explains format and cursor/pagination. But sql, index, and cursor parameters lack semantic detail.

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 a read-only SELECT on manifest's public columns, distinguishing it from sibling tools like grep_corpus or search. The reference to a contract adds specificity.

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?

Implies usage for reading manifest data with SQL, but does not explicitly state when to use over alternatives or provide exclusions. The performance hint about format is helpful but not a usage guideline.

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, so the read-only behavior is clear. The description adds the 20K-char cap, which is important and not in annotations. 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 very concise (one sentence) and front-loaded with purpose. It could benefit from a brief parameter explanation, but it is not overly verbose.

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 2 parameters and no output schema, the description is incomplete. It lacks essential parameter explanations, making it insufficient for correct invocation without additional 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?

Schema description coverage is 0%, so the description must compensate. However, it provides no information about the two parameters ('path' and 'index'). The agent has no guidance on how to use them.

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 ('Read'), the resource ('one facts/<schema>/*.json'), and the content type ('numbers/rates/thresholds'). It distinguishes from siblings like read_md or fetch by specifying the structured JSON nature.

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 implicitly indicates usage for reading structured facts files, but provides no explicit guidance on when to choose this tool over siblings. No alternatives or when-not-to-use are mentioned.

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 annotation, the description explains the verify parameter behavior: it recomputes content_hash and returns either verified:true or VERIFY_MISMATCH. This adds useful behavioral context about a conditional outcome.

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, front-loaded with the primary purpose. Efficient but could be structured with bullet points for clarity. Score 4 for being concise without being terse.

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 5 parameters with no descriptions in schema and no output schema, the description should cover return format and parameter roles. It only explains the verify behavior, leaving gaps for limit/offset slicing and index. Incomplete for an effective 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?

With 0% schema description coverage, the description should elaborate on parameters. It only partially explains verify. It does not clarify the meaning of path, index, limit, offset, or how they relate to the 'body slice' mentioned. The default and constraints in schema are not supplemented.

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 reads a single markdown file, specifying it includes frontmatter and a body slice. The verb and resource are explicit, and it distinguishes from sibling tools like read_facts or diff_md because it focuses on a single file read.

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 gives no guidance on when to use this tool versus alternatives like fetch (for URLs) or diff_md (for comparisons). It does not mention when not to use it or provide context about the intended scenario.

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, but the description adds behavioral context such as the ability to pass a result ID to fetch, and outlines the return structure. 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 concise sentences with no wasted words. Front-loaded with key purpose and output format, then mentions alternatives.

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 no output schema, the description explicitly defines the return structure. With only one parameter and clear sibling references, it is complete for this simple 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 description coverage is 0%, yet the description only implicitly mentions the query parameter. It adds no details about query format, constraints, or semantic meaning beyond the schema's type and length limits.

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 performs a library-wide search and specifies the output structure ('results[{id,title,url,text}]'), distinguishing itself from sibling tools like grep_corpus and read_md which offer finer control.

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 mentions when to use alternatives: 'Native tools (grep_corpus, read_md) offer finer control,' guiding the agent away from this tool for more specific searches.

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 provide readOnlyHint=true; description adds that it returns run_id, gates, integrity and notes pre-publish behavior. 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?

Extremely concise: three short sentences, front-loaded with key return fields and usage hint. No redundant 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?

For a simple read-only tool with one parameter and no output schema, description provides sufficient behavioral context and pre-condition. Minor gap: no explanation of the parameter.

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 has one parameter 'index' with constraints but no description. Schema description coverage is 0%, and description does not explain the parameter, leaving the agent to infer it from context.

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 'Published snapshot: run_id, gates, integrity' and 'Call first', indicating it checks snapshot status. This distinguishes it from siblings like 'fetch' or '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?

Explicitly says 'Call first' implying it should be used before other operations, and warns about pre-publish state. Lacks explicit when-not-to-use or alternatives, but context is clear.

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