guichet

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

Goes well beyond the annotations by clarifying that the call creates a live payment session but charges nobody by itself, that the return value is a URL, and that payment must be completed out-of-band by the human. That is a material behavioral fact (side effects, money movement boundary) not derivable from readOnlyHint=false / openWorldHint=true alone.

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 and the outcome, then the safety instruction, then the precondition — a sensible order. The parenthetical price/refund detail is useful but the sentence is slightly overloaded; minor trimming would tighten it.

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 two-parameter tool with an output schema and full annotation coverage, the description supplies everything an agent needs: what it creates, what it returns, the payment boundary, and the freshness precondition on the required argument.

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 adds a real constraint the schema cannot express — the submission_id must originate from submit_pwa and be less than 30 days old. The optional email parameter is left entirely to the schema, which is acceptable given its full documentation.

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 (create a Stripe Checkout link) plus the object it acts on: upgrading an existing submission to Fast-Track. It also names the concrete outcome ($19.99, 48 h publication, refund policy), which no sibling tool offers, so the agent can distinguish it from get_pwa/submit_pwa immediately.

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 prescribes the workflow: give the returned URL to the person you are working for and never attempt to complete the payment. It also states a hard precondition (submission_id from submit_pwa, under 30 days old), which is exactly the when-to-use/when-not guidance an agent needs.

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, the description discloses important behavior: it 'Returns found:false rather than an error when the slug is not in the catalog', which prevents the agent from misinterpreting missing results. It also adds a safety instruction about third-party listing content, which is valuable operational context not present in 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?

Four concise sentences with no filler. The primary purpose is front-loaded, followed by read-only status, not-found behavior, and a safety caution. 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?

With a single well-documented parameter, strong annotations, and an output schema present, the description covers the core behavioral expectations: read-only operation, not-found semantics, and content handling. Nothing essential is missing for an agent to invoke this 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 schema already fully documents the slug parameter with pattern, length, and description. The description reinforces that the slug comes from search_pwas, matching the schema, but adds no new semantic detail beyond that. With 100% schema coverage, a 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 description uses a specific verb and resource: 'Fetch one catalog listing in full by its slug'. It clearly distinguishes itself from search_pwas by indicating it retrieves one listing by slug, and names the source of the slug. This makes the tool's role unambiguous among 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?

The description says the slug is 'as returned by search_pwas', which implicitly tells the agent to use this tool after searching and when a specific slug is known. It lacks an explicit 'use this instead of X' statement, but the context is clear enough for correct tool selection.

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 and destructiveHint=false, so the safe-read profile is covered structurally. The description adds substantive context beyond annotations—the two review tiers, their costs, and turnaround times—though it does not discuss permissions, rate limits, or other operational constraints. That is a strong supplement but not exhaustive.

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?

Four short sentences, front-loaded with the core purpose, followed by pricing/timing, a quick safety signal, and a usage instruction. Every sentence contributes useful information; nothing extraneous.

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 zero-parameter read-only lookup with an output schema, the description covers what the tool contains, why it matters, and when to call it. No essential context 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?

The tool takes zero parameters, so there are no parameter semantics to document; baseline 4 applies. The description correctly focuses on what the tool returns rather than fabricating input details.

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 uses a specific verb (list) and resource (submission requirements), enumerates the exact content returned (required/optional fields, rules, categories, review tiers), and explicitly contrasts it with submit_pwa. An agent can readily distinguish it from sibling tools 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?

It gives direct when-to-use guidance: call it before submit_pwa rather than guessing a category. The alternative (submit_pwa) and the sequencing are explicit, leaving nothing to inference.

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 indicate read-only and idempotent behavior, but the description adds valuable disclosure: it never returns personal data, the handle is a lookup key rather than a credential, and stale handles over 30 days are rejected. It also states exactly which data is returned, going well beyond the annotation hints.

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 compact and front-loaded with the purpose, with each sentence carrying useful information. The only minor redundancy is 'Read-only,' which duplicates the readOnlyHint annotation, but it is not bloated enough to lower the score further.

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 single-parameter, read-only status tool, this description covers what it returns, where the ID comes from, important temporal constraints, and privacy guarantees. The presence of an output schema further reduces the burden, and nothing an agent needs 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 already explains the submission_id format and its non-credential nature. The description adds meaning on top by specifying the ID comes from submit_pwa and that handles older than 30 days are rejected, so it is more than a baseline 3.

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 starts with a specific verb+resource: 'Report where one submission stands.' It then enumerates the returned fields (app name, URL, submission date, tier, published status), which clearly distinguishes it from listing/searching tools like search_pwas and get_pwa. The explicit link to submit_pwa's returned ID anchors its role in the workflow.

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 clear context: call it with the submission_id returned by submit_pwa, and note that handles older than 30 days are rejected. It doesn't explicitly state when not to use it or name alternative tools for different needs, so it stops short of a 5.

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 useful behavioral context beyond annotations: results are capped at 20 regardless of requested limit, and listing text is third-party content that should be reported rather than followed. The read-only and idempotent traits are already in annotations, so the description does not need to repeat them, but the cap and content warning are valuable additions.

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 sentences, all informative and free of filler. The core action and return value are front-loaded, followed by important behavioral caveats. 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?

The description covers the purpose, output shape, API cap, and safety guidance, while the schema fully documents all parameters. With an output schema present and no nested objects or complex invocation requirements, nothing essential 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% and each parameter already has a meaningful description. The tool description does not add extra parameter-level meaning beyond what the schema provides, which meets the baseline for high schema coverage.

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 (search), a clear resource (the pwa.directory catalog), and what the tool returns (listing summaries with slug, name, description, category, tags, and URL). This clearly distinguishes it from siblings like get_pwa, which presumably fetches a single app rather than performing a catalog 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?

The description gives clear context: use this to search the PWA catalog and get listing summaries. It does not explicitly name alternatives or state when not to use the tool, but the search-and-summaries framing makes the appropriate use case evident.

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 the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), while the description supplies the substance: a moderation-queue write, an outbound receipt email to contact_email, human review before publication, a ~7-day latency, duplicate-suppression semantics, and a 30-day handle lifetime. The 'holding the handle authenticates nobody' note is a genuine security caveat not derivable 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?

Front-loaded with the action and its consequences, and nearly every sentence carries new information. There is mild redundancy between 'a human reviews it before anything is published' and the closing 'the queue is read by a person', which repeats the same fact.

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 an 8-parameter write tool with an output schema and full schema coverage, the description covers everything an agent needs: side effects (queue write, email), latency, idempotency, handle lifetime and its downstream effect on two siblings. Return-value details are correctly left 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% and every parameter already carries its own prose, so the baseline is 3. The description restates the idempotency_key contract (replay returns the first submission) and the contact_email receipt side effect, but adds no new syntax, constraint or format detail beyond what the schema documents.

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?

Opens with a specific verb and resource ('Submit one progressive web app for review'), immediately distinguishing it from read-oriented siblings like get_pwa, search_pwas and get_submission_status. The scope ('one app', 'for review') is precise enough that an agent can pick this tool without inspecting 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?

Gives clear context: free review ~7 days, human review required, and a gating rule ('Submit apps that exist and that you can name'). It also warns that the returned handle expires in 30 days and that get_submission_status and create_pro_launch_checkout will reject it afterwards, which routes the agent across siblings. It stops short of an explicit 'call get_submission_requirements first' instruction, so no named-alternative exclusion.

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