Readiness scorer — can an agent sign up to your SaaS?

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

The description discloses that the response varies based on scan status, returning only metadata while queued/running and full results when complete. This adds meaningful context beyond the readOnlyHint and idempotentHint annotations. It also lists specific result contents, including score, grade, rubric points, fix list, and unobservable items.

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 with no extraneous words; the first sentence states the action, the second explains the behavior. Information is front-loaded and each clause 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?

The description provides a complete picture of what the agent will receive, including the status-dependent behavior and the exact result components. Since there is no output schema, this is the primary source of return-value information. The single parameter is well-covered by the schema, and annotations cover safety and idempotency.

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 input schema already fully documents the single 'id' parameter with a description referencing readiness_request_scan, so the description adds little parameter-level detail. The phrase 'by id' reinforces the parameter's purpose but doesn't go beyond schema. With 100% schema coverage, a baseline score 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 clearly identifies the action as polling a scan by id, with a specific resource and purpose. It distinguishes itself from siblings by focusing on retrieving scan results rather than requesting a scan or fetching a verification token. The verb 'Poll' is precise and the status-dependent return behavior is stated.

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 'Step 3' marker and the explanation of status-dependent responses convey when to use this tool in the workflow. It implies it should be called after readiness_request_scan, and the schema reinforces that the id comes from that tool. It does not explicitly name alternatives or when-not-to-use, but the 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 readOnlyHint=true and idempotentHint=true. The description adds valuable context beyond that: it explains the token is deterministic (calling again returns the same value) and that nothing is stored. This reinforces the read-only nature and clarifies side effects, which is useful for an agent deciding whether to call it repeatedly.

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 two sentences with no fluff. The core purpose is front-loaded, and the additional details (determinism, storage, publication methods) are relevant and compact. Every clause 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?

For a simple one-parameter tool with no output schema, the description covers the essential return value (token and three ways to publish) and behavioral properties (deterministic, no storage). It does not describe the exact format of the token or the specific syntax of the publication methods, but given the simplicity, this is a minor gap and does not impede 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?

The schema covers the single 'url' parameter fully, describing it as a public https URL. The description does not add additional semantics about the parameter itself; it only uses 'URL's host' which is implicit. With 100% schema coverage, the baseline of 3 applies, and the description does not go beyond what the schema already provides.

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 action (returns the domain-ownership token) and a clear resource (the URL's host). It explicitly lists the three publication methods (DNS TXT, meta tag, .well-known file), which makes the tool's output unambiguous and distinguishes it from the sibling tools that get or request scans.

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 positions the tool as 'Step 1 of a readiness scan,' which tells the agent it is the first action in a sequence. It does not explicitly name alternatives or conditions for when not to use it, but the step ordering gives sufficient context for an agent to know this precedes readiness_get_scan or readiness_request_scan.

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 not read-only and not idempotent, and the description adds substantial behavioral detail: it bypasses human interaction, never solves CAPTCHAs, enforces a 3-scans-per-host-per-day limit, and returns failure modes with instructions. This goes well beyond the annotations without contradicting them.

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-load the core action, then cover return value, failure modes, rate limits, and the no-CAPTCHA behavior. Every sentence earns its place with no fluff.

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 mutating, rate-limited, stateful operation with no output schema, the description still provides return values (scan id, results URL), error conditions, prerequisites, and behavioral constraints. An agent has enough to know when to call it and what to expect.

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 single url parameter is already fully documented with format and example. The description adds the domain-ownership context and public-page requirement, but the schema already carries the essential semantics, so a 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?

States a specific verb and resource: verifies domain ownership and queues a Playwright probe that performs signup/acceptance/API key minting. The 'Step 2' marker and reference to readiness_get_verification_token clearly position it against the sibling tools readiness_get_scan and readiness_get_verification_token.

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 frames this as Step 2 after obtaining the verification token, and specifies the prerequisite that the domain must carry that token via DNS TXT, meta tag, or .well-known. It does not explicitly say 'use readiness_get_scan to poll', but the workflow context and return values make the intended usage clear.

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