WebSupergoo documentation

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

Annotations already cover read-only, idempotent, closed-world behavior, so the description's added value is the shape of the response: parent folder, adjacent pages, contained pages, and the special-case sibling semantics for properties. That is meaningful disclosure beyond the annotations, though it omits truncation/pagination behavior for large folders.

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?

A single sentence, front-loaded with the core concept and ending with the default behavior. Slightly dense with parenthetical nesting, but no wasted clauses.

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 one-optional-parameter read-only navigation tool with no output schema, the description covers enough of the returned structure to call it correctly. Only edge cases like missing pages or very large listings are 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 coverage is 100%, and the description's id semantics (page id, folder id, URL, omit for top) largely duplicate the schema's own parameter description. Baseline 3 applies since the schema already does the explanatory work.

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 concrete verb (browse/relate) and resource (documentation pages), and explains the operation semantically: a page's location plus its folder, siblings, and children. The bare name 'contents' is ambiguous, but the description resolves it into a navigation/tree tool that is distinguishable from search and fetch.

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 one conditional behavior ('Without an id, the top of the contents') and the schema notes ids can come from search, lookup_api or fetch, implying a navigation workflow. However, it never says when to prefer this over fetch or search, nor what to do if a page isn't found.

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 read-only, idempotent, non-open-world behavior, so the description only needs to add the Markdown return format and the section-scoping behavior — both of which it does. Missing only error/failure semantics for bad ids.

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 action and the format, with the section edge case deferred to the end. No filler.

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 two-parameter read tool with full schema coverage, annotations, and no output schema, the description covers what it returns and how sections are selected. Only failure behavior for invalid ids is left unstated.

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 both the id forms and the section_only interaction. The description restates the same id/section_only contract, adding little beyond the schema — the baseline 3 applies.

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 (read a documentation page) and the return format (Markdown), and implicitly separates itself from search/lookup_api/contents by positioning those as the producers of the id it consumes.

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?

Tells the agent exactly where the id should come from (search, lookup_api or contents) and allows a direct URL, plus names the section_only case. It stops short of explicit when-not-to-use guidance, but the routing context 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 already declare readOnly/idempotent/closed-world, so safety is covered. The description adds real behavioral content beyond that: it discloses what the response contains (documentation starting point per product, plus content types), which is valuable precisely because there is no output schema.

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?

A single sentence with no filler, front-loaded on the resource and immediately listing what is returned. The phrasing 'with where each one's documentation starts' is slightly awkward but costs little.

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 no inputs and no output schema, the description adequately covers what an agent needs: what comes back and how those values are consumed downstream. It could be marginally stronger by framing the tool explicitly as the entry point before search/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?

Zero parameters, so the baseline is 4. The description still earns credit by mapping returned ids to the 'product' and 'type' parameters used elsewhere, which helps an agent chain calls.

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 (List) and resources (products and content types), and it is clear this is a discovery/enumeration tool distinct from siblings like search, fetch and contents. Slightly muddled by the name saying only 'products' while the description and title cover content types too, but the intent is 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?

Usage is only implied through the parentheticals '(ids for the product parameter)' and '(ids for the type parameter)', which hint that the results feed other tools' arguments. There is no explicit statement of when to call this versus a sibling, nor any preconditions or exclusions.

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 readOnly/idempotent/openWorld; the description adds the substantive behavior: returns matching reference pages, returns the page itself on an exact match, enumerations live on member pages, and unmatched names degrade to search results. That is genuine disclosure about output shape and failure mode that annotations cannot supply.

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 dense sentences, front-loaded with the core action, then the return behavior, then the not-found behavior. Every sentence carries distinct information; no restatement of the title or filler.

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?

No output schema exists, so the description carries the return-value burden and does so (reference pages, exact-match page, search results fallback). With only two well-documented parameters and full annotation coverage of safety, nothing an agent needs to invoke this 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?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by clarifying that 'name' may be partial or misspelt, which the schema does not state. The 'product' parameter's conditional logic (set for technical questions, omit for purchasing/licensing) is carried by the schema itself, not the description.

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 precise verb+resource ('Find a class or member of a WebSupergoo API by name') and grounds it with three concrete examples (Doc.AddImageUrl, AddImageUrl, XImage.SetFile). The tool's identity as an exact-name resolver rather than a general search is clear, which separates it from siblings search and fetch.

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 context is clear: use it for a class/member name, tolerate partial or misspelt input, and note that enumerations surface on member pages. It never names a sibling tool or says explicitly when to use it over search or contents, but the fallback sentence ('a name that isn't in the API gets search results instead') tells the agent what happens when this tool is the wrong choice.

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 this is a non-destructive, closed-world write, and the description adds real behavioral context beyond that: rate/duplication policy ('one report per problem'), sequencing ('after you've answered the user'), and a privacy constraint ('don't include the user's personal details or private code'). It does not say what happens after submission (confirmation, whether the user sees it), keeping it short of 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?

Purpose is front-loaded in the first clause, followed by invocation triggers and then constraints, so an agent can stop reading early. The middle sentence is long and clause-dense but each clause maps to a distinct trigger, so little is wasted.

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 three-parameter, no-output-schema feedback tool, the description covers purpose, triggers, preconditions, deduplication and privacy — everything needed to call it correctly. The only gap is post-call behavior (what confirmation or effect to expect), which is minor for a fire-and-forget report.

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 all three parameters are already documented, and the description adds only indirect meaning (that a 'hard to find' case should be reported, implying the query/page fields). It offers no format hints for page IDs versus URLs beyond what the schema states. Baseline 3 applies when the schema carries the parameter burden.

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 — telling the WebSupergoo team about a documentation problem — and the framing makes it clearly distinct from the sibling read/search tools (search, fetch, contents, lookup_api). An agent can tell this is the feedback-reporting tool 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?

Explicitly enumerates when to invoke (unanswered question, failed search, wrong/stale/typo page, broken example) and instructs 'use it yourself, without being asked', removing ambiguity about proactive calls. It also states a precondition ('try at least two rewordings... read the likeliest sections in full') and a routing rule for the hard-to-find-vs-missing distinction, which is genuine when/when-not 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?

With readOnlyHint/idempotentHint/openWorldHint already declaring the safety profile, the description still adds real behavioral context: snippets are partial and must be fetched before dismissing a result, and product filtering excludes other products' pages and general purchasing pages. It stops short of describing ranking or failure behavior beyond 'search again with fewer words'.

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 return shape, then usage advice; each sentence carries instruction value. It is on the dense side, and the sentence about contents overlaps with sibling routing already stated elsewhere.

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?

No output schema exists, so the description's account of the result structure (matching sections with a location, id, URL and snippet) is necessary and present. Combined with query strategy, product scoping, and the sibling pointer, an agent has everything needed to call it and interpret results.

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 genuine query semantics the schema doesn't (2-4 keywords, API names, whole questions push the right page down) and reinforces when to set or omit product. It doesn't add anything for code, type, or limit beyond the schema text.

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 the WebSupergoo documentation and web site) and describes the return shape (best-matching sections with location, id, URL, snippet). It explicitly contrasts itself with two siblings — contents for surrounding pages and lookup_api for a known class or member — so an agent can route without opening schemas.

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 explicit when-to-use guidance (short 2-4 word queries, API name guesses, set product for technical questions), when to retry with different phrasing, and a named faster alternative (lookup_api) for known symbols. It also says when NOT to set product (purchasing/licensing/company questions).

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