Pasportoo Website Audit

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description's 'nothing is ordered' is a mild restatement rather than new information. Its real added value is enumerating the returned content (price, delivery time, limits, ordering path), which matters because there is no output schema. It does not say whether this data is static documentation or fetched live, which is the one remaining behavioral gap.

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 dense sentence with the scope front-loaded and the read-only constraint placed last for emphasis; every clause maps to actual deliverable content. The nested parenthetical is slightly heavy but carries real substance rather than 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 zero-parameter informational tool with no output schema, the description covers what an agent needs: what is audited, what is delivered, and what commercial details come back. It falls just short of complete because it never states the relationship to prepare_website_audit_order or clarifies whether the offer details are static or retrieved live.

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; the description correctly says nothing about inputs, which is appropriate given the empty object schema.

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: 'Describe Pasportoo's paid audit of a public website,' and then enumerates exactly what that description contains (coverage areas, price, delivery time, limits, ordering). The closing 'Read-only; nothing is ordered' implicitly separates it from the sibling prepare_website_audit_order, so an agent can tell these apart 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?

The phrase 'Read-only; nothing is ordered' plus the mention of 'how the owner orders it' establishes this as the pre-purchase informational step before prepare_website_audit_order. However, it never explicitly names the sibling or states the when-to-use condition ('call this before preparing an order' / 'when the user asks about pricing or coverage'), leaving the routing 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing what each entry reports — orderability and what has been measured — which tells the agent this is a status-bearing catalogue rather than a bare name list.

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 with the resource named first and the returned attributes trailing. The parenthetical enumeration is dense but earns its place by telling the agent what coverage to expect; slightly awkward phrasing around "what has been measured" costs a point.

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 describing return values and does so at a summary level (orderability, measurement status). It stops short of naming the fields or shape, which is a minor gap for a zero-parameter read tool.

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. Schema coverage is 100% and the empty object schema is self-explanatory.

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 resource ("Pasportoo's specialist agents") and enumerates the agent categories covered (website audit, accessibility, speed and SEO, code security, pentest). This clearly separates it from the sibling offer/order tools, which act on a single agent rather than enumerating the catalogue.

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 catalogue framing implies this is the discovery step before get_website_audit_offer or prepare_website_audit_order, but the description never says so explicitly. There is no stated when-to-use or when-not-to-use guidance relative to the two siblings.

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 mark this read-only and closed-world, and the description adds real context beyond them: nothing is ordered, charged or sent to the site, and authorisation plus payment happen on the linked page. It stops short of saying what happens on an invalid or unreachable URL.

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 tight sentences, front-loaded with the core action and output, followed by the trigger and then the safety boundary. 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?

For a two-parameter read-only tool with no output schema, the description covers what is returned (a prefilled order link) and what does not happen. Slight gap around failure behaviour for invalid URLs, but nothing essential to invocation 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 both the url format and the goal enum meanings are already fully documented in the schema. The description only restates that the address must be public https, adding no syntax or constraint detail beyond that 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 specific verb and resource pair: validate a public https address and return a prefilled order link for its owner. The output is concrete, and the negative clauses ('does not order, charge or contact the site') separate it from the adjacent offer/agent 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?

Gives a clear trigger condition: use when the user wants their own website checked for bugs, security problems or UX issues. It does not name when to prefer get_website_audit_offer or list_pasportoo_agents, so the sibling routing is left to inference.

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