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

Annotations already cover safety (readOnly, idempotent, non-destructive, open-world), so the bar is lower, and the description still adds real operational context: a two-stage retrieval strategy (page-preview endpoint first, then HTML parsing fallback) and the fact that section text is capped and flagged via "truncated". This tells the agent results may be partial and where the cap signal lives. It stops short of explaining failure modes when both retrieval paths fail.

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?

Front-loaded with what the tool returns, followed by the retrieval strategy and cap caveat in two compact sentences. No filler. The trailing parenthetical reference to the output-schema field "truncated" is slightly indirect but functional.

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?

An output schema exists, so return-shape explanation is not required, and annotations carry the safety profile, which the description sensibly does not repeat. The remaining gap is the sole input: slug's expected format is documented nowhere. Adequate but incomplete for actually invoking 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?

There is exactly one parameter, slug, with 0% schema description coverage, so the description carries the full documentation burden. It never defines the slug's format, whether it is derived from the page URL, or whether it is case-sensitive. "Grokipedia page" only loosely implies the identifier, leaving the agent to infer a required input shape.

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?

States a specific verb and resource ("Fetch a Grokipedia page") and enumerates what comes back: title, summary, sections, citations, URL. This makes it distinguishable in kind from get_page_section and get_page_citations, which return subsets. However, it never explicitly contrasts itself with those siblings, so the differentiation is inferred rather than stated.

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?

There is no explicit when-to-use or when-not-to-use guidance, and none of the three siblings are named. An agent must guess that this is the aggregate call versus the narrower get_page_section/get_page_citations. Listing returned fields hints at that relationship but does not state it.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description correctly invests in what annotations cannot say: 'sections' is matched by exact URL and is [] when never cited inline; when the article has no usable inline markers (HTML fallback) 'sections' is null and 'section_mapping' is 'unavailable', and mappings are never guessed. That edge-case disclosure meaningfully tells the agent when to distrust the mapping.

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?

Front-loaded with the one-line purpose, then the return-shape detail, then terse Args. Every sentence carries information, though the mid-paragraph fallback/null explanation is dense and slightly harder to scan than a short bullet would be.

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?

An output schema exists, so return values needn't be spelled out, and yet the description goes further by explaining the semantics of 'sections' and 'section_mapping'. With two well-narrated parameters and annotations covering safety, an agent has what it needs; only the absence of any routing guidance versus siblings keeps it short of perfect.

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. It defines include_context semantically ('also return up to 3 short text snippets preceding each marker'), which is more than the schema's bare boolean-with-default, and names the context behavior. The slug parameter gets only 'Page slug', leaving its format still implicit.

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?

States a specific verb and resource ('Return the citations / references for a page') plus the added value ('with where each is cited'). This is clearly distinct from the siblings get_page, get_page_section, and search, so an agent can pick it without opening the schema.

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?

Usage is implied — you call it to get citations for a known page slug — but the description never states when to prefer it over get_page/get_page_section or any prerequisites (e.g. that the slug must resolve to an existing page). It offers no explicit exclusions or 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 readOnly/idempotent/safe, so the bar is lower; the description still adds real behavior beyond them — the two-stage heading matching fallback and the conditional include_subsections semantics ('if the section's own body is empty... return subsections' text'). It omits the not-found behavior, keeping it from a 5.

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?

Front-loaded with the core action in the first clause, then a compact Args block. Only the 'subsections always lists the nested headings' aside is slightly under-explained relative to its brevity.

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?

An output schema exists so return values needn't be described, and annotations cover the safety profile. Given three params at 0% schema coverage, the description supplies the needed parameter and matching detail; only the failure case is unaddressed.

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 — and it does, documenting all three parameters including the non-obvious conditional meaning of include_subsections and its default, plus an example slug. Minor gap: no guidance on heading format edge cases.

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?

States a specific verb+resource ('Return one section') and clarifies the lookup semantics versus the whole-page sibling get_page. It doesn't name siblings explicitly, but 'one section' vs a page-level tool is easily inferred.

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 matching rule (exact case-insensitive first, else heading containing the text) gives useful context for when this tool will succeed, but it never says when to prefer it over get_page or search, nor what happens on no match.

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, and destructiveHint=false, so the safety profile is covered. The description adds that this hits a 'full-text index' (as opposed to fetching a page), which is useful, but says nothing about ranking, result shape, 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?

Front-loaded with the purpose in one line, followed by a compact Args block. Every element earns its place, though the Args formatting is slightly mechanical for a description field.

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, return values need not be described, and annotations cover safety. Still missing is any hint of query syntax or how results relate to the sibling get_page tools, which an agent needs to chain a search into a fetch.

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 carries the full burden and largely meets it: it documents all three parameters, adds a range constraint for limit (1-50) that the schema lacks, and restates defaults. It stops short of explaining query syntax (phrases, operators) or result ordering.

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?

States a specific verb and resource ('Search Grokipedia full-text index'), which is clear enough for an agent to know it performs a full-text query. However, it never distinguishes itself from the sibling retrieval tools (get_page, get_page_section, get_page_citations), leaving the search-vs-fetch boundary to inference.

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?

There is no when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The description says only what the tool does, not when an agent should reach for it over the page-fetching tools.

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