Brasspage

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

Annotations cover read-only and open-world behavior, and the description adds context beyond them: the service is free and capped at 10 checks per IP per day, which materially affects retry strategy. It does not say what happens on an unreachable URL or how failures are reported.

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 scope; the nine-item checklist is long but earns its place since there is no output schema to describe the returned checks. No filler sentences.

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?

Because there is no output schema, the enumerated checklist is essential and present, and the rate limit is disclosed. Minor gaps remain: no indication of result format (pass/fail per check) or behavior on error, but nothing that would prevent an agent from calling it 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?

With one parameter at 100% schema coverage plus an inline example ('yourbusiness.com'), the schema carries the load. The description adds only a mild constraint ('one small business homepage'), implying the URL must be a homepage rather than a deep link, but no format rules beyond the schema's own example.

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 ('check') and a precisely scoped resource ('one small business homepage'), then enumerates the nine checks so the agent knows exactly what the tool inspects. This is clearly distinct from siblings like request_redesign or live_numbers without needing to name them.

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?

'One small business homepage' and 'Up to 10 checks a day for each IP address' establish scope and a hard rate limit, which implicitly tells the agent when the tool applies. However, there is no explicit guidance on when to use this over the sibling tools or what to do when the daily quota is exhausted.

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 openWorldHint=false, so the safety profile is covered. The description adds a useful temporal scope signal ('today's' figures, i.e. a live snapshot rather than history), but says nothing about freshness cadence, caching, or what a consumer receives. That is additive but thin against the lower bar set by 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?

A single front-loaded sentence that leads with the owner and the temporal qualifier, then lists the payload items; nothing is padding. The dense jargon makes it terse to the point of opacity, but no sentence 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?

With no parameters, no output schema, and annotations covering safety, the description's remaining job is to say what comes back — and it does, naming four distinct data categories. It is only short of a 5 because it never clarifies what 'line from Tack' or 'day of the experiment' actually mean, leaving the response shape partly guesswork.

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 is nothing for the description to disambiguate; baseline 4 applies. No misleading parameter language is present.

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 resource (today's real numbers) and enumerates its parts: money in, money out, experiment day, and today's line from Tack. That is far more than a restatement of the name. It loses a point because domain jargon ('Brasspage', 'Tack', 'the day of the experiment') is unexplained and siblings (check_site, pin_tack) are never referenced to sharpen the boundary.

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?

Only the word 'today' implies when this is appropriate; there is no explicit when-to-use, when-not-to-use, or comparison to check_site or pin_tack. An agent must infer entirely from the resource nouns whether this is the right tool.

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 declare readOnlyHint=true, and the description is consistent with that, adding valuable context the annotations cannot convey: no payment is taken here, notes are reviewed before going up, and rejected notes are refunded. It does not disclose how long the payment link is valid, whether it is single-use, or what the tool returns for an invalid note other than the refund statement.

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 sentences, front-loaded with what the tool does, then the most important disambiguation (no payment taken), then the review/refund policy. Every sentence earns its place with no repetition of schema content.

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 correctly identifies the return value as a Stripe payment link, and it covers the moderation and refund behavior that would otherwise be invisible. Minor gaps remain around link validity and failure modes, but nothing essential to calling it 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 name, note, and color are all already documented with length and word constraints and an enum default. The description adds nothing about the parameters themselves, so 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 and resource: checks a note for the Tack Board and returns the $3 Stripe payment link. It also pre-empts a likely misreading of the name 'pin_tack' by clarifying that it does not itself post or take payment. There is no explicit differentiation from siblings, but check_site, live_numbers, and request_redesign are unrelated enough that this is not a real ambiguity.

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: an agent can infer it should call this when it has a name and note to submit, before payment. There is no explicit 'use this when' clause, no stated prerequisites, and no guidance on what to do with the returned link or what to do if a note is rejected beyond the refund remark.

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 openWorldHint=false, and the description reinforces this with explicit side-effect disclosures: 'sends no email and stores nothing.' The crucial behavioral trait — that a human must complete the action outside the tool — is disclosed, which the annotations alone would not convey. It stops short of covering link expiry or failure modes.

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 sentences with zero filler. The return value comes first, the required human action second, and the negative side effects last — a well front-loaded structure.

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 carries the burden of explaining the return value and does so ('a link ... with the website and email filled in'). Combined with the side-effect disclaimer, an agent has everything needed to call it and to tell the user what to do next.

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 two parameters are already fully documented as the business website and owner email. The description only adds that both values are prefilled into the form, which is mild extra meaning over the schema baseline.

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 concrete verb and resource: it returns a prefilled link to a free redesign form, with the website and email already populated. That is specific enough that an agent can immediately tell it apart from check_site, live_numbers, and pin_tack, none of which produce a form link.

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 sentence 'The business owner must open it and send the form themselves' implies the handoff workflow, but the description never says when to reach for this tool versus another, nor does it name any alternative or exclusion. Usage is implied rather than stated.

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 declare this is not read-only and not open-world. The description adds meaningful behavior beyond that: submissions are queued, free, human-reviewed by Tack before appearing, and restricted from links, phones, ratings, or reviews. It does not cover auth or rate limits, but the moderation and queue behavior are well disclosed.

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 front-loaded with the core action and purpose, followed by useful constraints. Every sentence earns its place: the URL, free status, moderation note, and content exclusions all add relevant context without 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 write/queue tool with full schema coverage and no output schema, the description covers submission behavior, moderation, cost, and content restrictions. It could mention the optional color parameter or what happens after review, but it is otherwise sufficient for correct invocation.

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 baseline is 3. The description restates the four required inputs and the 8-word note limit, but it omits the optional 'color' parameter and largely repeats what the schema already 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?

The description uses a specific verb and resource: 'Queues a favorite small shop for Brass Street', and names the required inputs. It is clear what the tool does, but it does not explicitly distinguish itself from siblings such as pin_tack or request_redesign.

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 by 'Queues a favorite small shop for Brass Street' and the content exclusions, so an agent can infer this is for adding shops. However, there is no explicit when-to-use guidance, no when-not-to-use guidance, and no mention of alternatives among the sibling tools.

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