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

Annotations cover the safety profile (readOnly/openWorld/non-destructive), so the bar is lower, but the description still discloses live-site reads, 3-redirect follow limit, 50 KiB truncation with a link to the full page, no auth, no caching, and a full error taxonomy including which error is retryable. That is behavior an agent cannot infer from any structured field.

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?

Information is front-loaded: what it returns, then what it takes, then runtime behavior, then errors. Dense but nearly every clause carries actionable content; the redirect/truncation clause is a single compact sentence rather than sprawl.

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 the description does not need to detail the return object, yet it still hints at the fields. For a single-parameter read tool with annotations and an output schema, everything an agent needs to call it correctly and interpret failures is present.

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 would be a 3. The description adds real meaning beyond the schema by framing the parameter's provenance (a bundle link or a search result URL) and by tying a bad path to specific errors (not_found vs invalid_input for paths resolving outside the docs).

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 ('Returns one CometChat documentation page in full') and even names the return shape (markdown with title, url, section). The contrast with search_cometchat_docs is explicit, so an agent can route without opening either 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?

Gives the exact precondition ('Takes a url or path already in hand: a docs link from a bundle, or a result url from search_cometchat_docs') and names the alternative for the opposite case ('a topic or API name goes instead, since that is not a path'). This is a textbook when/when-not split.

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 only declare read-only and non-destructive; the description adds substantial context beyond them: whole pages in order, a 60 KiB document budget, oversized pages listed under 'More pages' rather than truncated (with a paragraph-level cut exception for an oversized first page), a 10-minute serve window with background refresh, graceful degradation via the previous or partial bundle, and backend_unavailable only when nothing loads and nothing is cached. No key or account required is also stated, which annotations cannot express.

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 is returned, then alternatives, then the parameter trap, then operational behavior — a sensible order. The prose is dense with semicolon-linked clauses and a long final sentence about failure modes, which costs a little readability, but every sentence carries information an agent needs to call the tool correctly.

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 need not be restated, and the description still covers the operational envelope an agent must anticipate: content ordering, size limits and truncation, caching staleness, and degraded/error responses. Nothing material for correct invocation is missing given a single required 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 coverage is 100% and already documents the identifier's format, so the baseline is 3; the description earns an extra point by clarifying that the value is an identifier, not a title or framework ('react-uikit-quickstart', not 'React UI Kit' or 'react'), and by mapping the two distinct error outcomes (unknown_bundle with the valid list versus invalid_input) to the kinds of wrong input. It does not add syntax beyond the schema, so it stops short of 5.

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?

Names a specific verb and resource ('Returns one CometChat implementation bundle') and immediately defines the artifact: the scenario's documentation pages compiled into one markdown document, each headed by its source URL, plus related paths, prerequisites, and a last_verified date. The following sentence enumerates the eleven covered scenarios, so an agent knows exactly what content surface this tool owns versus its siblings.

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 routes between siblings: list_cometchat_bundles names the bundles, search_cometchat_docs is the fallback for a topic no bundle covers or for a single reference page, and fetch_cometchat_doc_page covers the single-page case. Both the when and the when-not conditions are stated, not implied.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered; the description still adds real behavioral context beyond that: no key or account required, no network connection opened by the listing, the set is fixed at startup, and repeat calls return identical bundles. That idempotence and auth-free guarantee is exactly what an agent needs and is not in 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?

Three short paragraphs, front-loaded with the definition and immediately followed by invocation facts and then fallback routing. Every sentence carries information an agent would otherwise have to guess: the enumeration's completeness, its ordering, and where to go when it does not apply.

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 need not be documented, yet the description still summarizes the per-bundle fields and the 'any' framework sentinel. Combined with the idempotence and no-auth notes, nothing an agent needs in order to call this zero-argument tool correctly is missing.

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 are zero input parameters, which sets the baseline at 4. The description reinforces this by explicitly stating that no parameters are required and that there is no filter, paging or cap, so an agent will not go looking for optional arguments that do not exist.

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 a specific verb and resource ('Lists every CometChat implementation bundle') and then defines what a bundle actually is (setup scenarios whose docs pages get_cometchat_implementation_bundle compiles by identifier), which distinguishes it from every sibling. It also names the fields returned (title, framework, last_verified), so an agent knows the shape of the catalog before calling.

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 gives clear positive context (one call returns the complete set, no filters or paging needed) and explicit negative routing: for an uncovered topic or a single reference page, use search_cometchat_docs instead. It stops short of explicitly telling the agent to call this first to discover identifiers before invoking get_cometchat_implementation_bundle, so the discovery workflow is left implicit.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds substantial non-annotation context: match/fallback ranking, empty list rather than error on no match, snapshot staleness versus the live site, error codes, and the per-IP HTTP rate limit with 429/Retry-After. That is well beyond what the annotations provide.

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 purpose and sibling routing before behavioral detail, and every paragraph is ordered by likely need. It is dense and long, though — the '4 to 8 distinct keywords ... half weight' explanation is more mechanism than an agent strictly needs to choose or call the tool.

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 3-parameter search tool with an output schema and full annotation coverage, nothing essential is missing: staleness, empty-result semantics, error codes, rate limiting, and no-auth are all stated. Return-value explanation is appropriately delegated to the 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 description coverage is 100%, so a 3 is the floor; the description goes further by explaining cross-parameter behavior the schema cannot — that limit caps returned rows but never totalAvailable, and that there is no offset. It also clarifies that a version keyword in the query does not restrict results, pointing at the version filter instead.

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 (searches) plus the exact resource scope — all CometChat documentation across named product areas — and the return shape (ranked excerpts with each page's url). It is immediately distinguishable from fetch_cometchat_doc_page (full page retrieval) and the bundle tools.

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 routes the agent: 'When a page's url or path is already in hand, fetch_cometchat_doc_page returns that page in full', and 'for a common setup scenario ... list_cometchat_bundles names the implementation bundles'. Both the when-to-use and the when-to-use-something-else conditions are stated.

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