Private AI Tools

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

Well beyond the readOnly/idempotent annotations, it discloses result cardinality (up to 8), ordering (best first), what each result contains (page URL), the partial-match fallback signal, and the important privacy behavior that files never reach the server or assistant. It also gives the agent an explicit operating instruction to pass the link to the user.

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 front-loaded sentences with the search scope and example queries first, then the return contract, then the browser-execution constraint. The parenthetical category list ('PDF, image, video, audio, developer, data, calculators…') is slightly noisy but does convey topical coverage.

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 output schema, the description still covers everything the agent needs: what is searched, result count and ordering, the URL to relay, how weak matches are signaled, and where the actual processing occurs. Nothing material for a correct invocation and response handling 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 description coverage is 100%, so the enum of languages, the default-language rule and the query phrasing are already fully documented in the schema. The description reinforces this with example query strings but adds no format or syntax detail beyond what the schema states, so the baseline of 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?

The description opens with a specific verb and resource ('Search the 144 free tools'), scopes it by category and gives concrete query examples such as "compress pdf" and "json to yaml". It does not explicitly contrast itself with the get_tool and list_tools siblings, so an agent must infer that this is the search entry point rather than a fetch-or-enumerate one.

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: search by task phrase, then hand the resulting link to the user since execution happens in their browser. It also explains the fallback condition (closest matches returned with partial: true). It stops short of naming the sibling tools and when to prefer them over a search.

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 annotations already establish this as a read-only, idempotent, closed-world operation, so the bar is lower, and the definition adds genuinely new behavior: the tools execute in the user's browser, the user must be handed the link, and files never reach the server or the assistant. That execution-location detail is exactly the kind of context annotations cannot express. Rate limits or failure modes for an unknown slug are not covered.

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, scope front-loaded in the first clause, no filler. The middle clause listing all returned fields is dense but earns its place given there is no output schema.

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 output schema, the definition must describe return values, and it names the four field groups returned. It also covers the key operational constraint, execution in the browser, and that files stay local. What is missing is minor: behavior on an unknown or ambiguous slug.

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 both parameters are fully documented in the schema, including the enum and the localized-slug/URL fallback. The description only adds that the slug originates from find_tools or list_tools and that URLs exist in every language, which is marginal over the schema. The baseline of 3 is appropriate.

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 definition states a specific verb and resource, "Details of one tool by its slug", and immediately identifies the fields it returns: name, description, page URL per language, and in-page WebMCP agent tools. Referencing find_tools and list_tools as the source of the slug cleanly separates it from those 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?

It tells the agent where the slug comes from, namely find_tools or list_tools, and instructs "give the user the link" because the tools run in the user's browser. The description implies the single-item lookup role but never explicitly states when to prefer it over list_tools or find_tools.

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, and closed-world, so the safety profile is covered. The description adds meaningful context beyond them: tools execute in the user's browser and files never reach this server or the assistant, which tells the agent this is a privacy-preserving pointer lookup rather than a compute call. Return shape is only partially described (page URL only).

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 short sentences, front-loaded with the core operation and followed by the privacy/presentation note. No redundancy, though the second sentence compresses two distinct ideas (browser execution and instructing the agent to hand over the link) into one clause.

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?

This is a simple two-optional-parameter listing tool with no output schema, and the description covers scope, filtering, and that each entry carries a page URL. The one gap is that the output listing format and default ordering are not described, but nothing required to call it 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% and both enum parameters are fully documented in the schema, including all category and language values, so the schema carries the burden. The description adds only the framing that category is an optional narrowing filter and that results are localized; baseline 3 is appropriate.

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 names a specific verb and resource ("List every tool of Private AI Tools") and states the scope: all tools or one category, each with its page URL. That distinguishes it from get_tool (single item) though it never names find_tools explicitly, so the boundary with search is left implicit.

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 rather than stated: enumerate everything or narrow by category. The closing instruction "give the user the link" is genuine usage guidance for presenting results. However, there is no explicit when-not or routing to find_tools for keyword-style lookups, which is the main ambiguity an agent faces.

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