Growth Radar

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotent=true, destructive=false) by disclosing caching semantics (stored audit under a day old is returned immediately), worst-case latency (~25s), an async 'running' status that completes in the background, and rate limits scoped per address and per site. These are exactly the operational facts an agent needs to plan retries and avoid hammering the tool.

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-loaded with purpose and followed by caching, timing and rate-limit behavior in that order of importance. No filler or repetition of the title.

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 does the work of explaining what comes back (an audit covering four categories plus a fix per failing check, or a 'running' status). It does not sketch the response fields beyond that, but for a single-parameter audit tool the agent has enough to call it and interpret the immediate outcome.

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% for the single 'domain' parameter ('A public domain or URL, e.g. example.com'), so the description starts from a 3 baseline. It only adds the constraint that the site must be public, which is marginally useful but does not add format or normalization detail beyond the 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?

States a specific verb and resource ('Audit any public website') plus the exact dimensions covered (SEO, AI-search visibility, speed, structured data) and the output shape (a fix for every failing check). Differentiation from the sibling get_site_audit is only implicit, conveyed through the 'returns the stored audit... otherwise runs a fresh one' sentence rather than by naming the alternative.

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 operational context: no account required, free use is rate-limited per address and per site, and the agent is told what to do when the result is not ready ('call again shortly'). It lacks an explicit when-to-use-this-instead-of-get_site_audit statement, which is the one remaining gap.

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 cover readOnly, idempotent, non-destructive and closed-world, so the bar is lower, yet the description still adds real value: it discloses the returned contents (score, failing checks and their fixes), the empty-state message, and that no account is required. It does not mention freshness/staleness of the stored audit, which is the main remaining 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?

Two tight sentences with the core action front-loaded and the caveats ('Says so when none is stored', 'Needs no account') following. No filler or restatement of the name.

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 steps in to list what comes back, and it covers auth and the empty case for a simple one-param read tool. Only the age/freshness of the stored audit is left unspecified.

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% with a single, well-described 'domain' parameter, so the schema carries the burden. The description reinforces 'public site' but adds no format or syntax detail beyond what the schema already specifies, which is the baseline-3 case for a one-parameter tool.

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 ('read the latest stored audit of a public site') and immediately differentiates via 'without running one', which contrasts with the audit_site sibling. It stops short of naming audit_site, so the contrast is implied rather than pinned to the sibling's name.

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?

'Without running one' implies the alternative is to run an audit, and 'Says so when none is stored' signals the empty-state path so an agent knows it need not pre-check. What's missing is an explicit instruction to fall back to audit_site when no stored audit exists.

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