Agent Ready Report

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that by disclosing the shape of the returned explanation (definition, rationale, test method, pass criteria, sources), which is valuable given there is no output schema.

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, no filler. The purpose and the content of the explanation are front-loaded, and the behavioral instruction for the no-argument case follows immediately. 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 single-parameter, read-only lookup tool with no output schema, the description is nearly self-sufficient: it says what it explains and what the explanation includes, and annotations carry the safety profile. Only a note on what happens with an invalid or unknown check_id 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 the check_id parameter is fully documented in the schema, including the enum and the instruction to omit it. The description's "call with no check_id to list every check" largely restates the schema rather than adding new semantics, so the baseline of 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?

The description names a specific verb (explain) and a specific resource (one agent-readiness check), and even enumerates the five things the explanation covers. It is trivially distinguishable from the sibling scan_website, since one explains a single check while the other runs a scan.

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 clear operational guidance for the optional parameter: "Call with no check_id to list every check," which tells the agent exactly how to use the tool in the no-argument case. It does not explicitly state when to prefer this over scan_website or what to do with a returned explanation, but the usage context is unambiguous.

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 readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new context: 5-30 second latency, the scoring rule that commerce checks are only scored for sites that sell online, and the 35-check scope. It does not note rate limits or whether the scan is cached, hence not a 5.

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: the first sentence states the action and the report shape, with the check lists and the when-to-use clause following. The exhaustive enumeration of 35 checks is dense, but it earns its place by letting an agent judge coverage before invoking. Slightly heavy, but not padded.

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 return-shape burden and does so: it says the response reports which checks pass, which are missing, and explains each check, plus latency and the conditional scoring rule. It lacks detail on result size or any truncation behavior, which keeps it short of 5.

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 url, detail and sells_online are already fully documented, making 3 the baseline. The description reinforces parameter meaning indirectly ('in plain English and technically' maps to detail; 'sites that sell online' maps to sells_online) but adds no syntax or format 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 (scan) and resource (public website) plus the exact output intent: readiness for AI agents and AI search, with pass/fail/missing checks. It enumerates the three check groups and the concrete signals covered, so an agent knows precisely what this does. The sibling explain_check is not named explicitly, but the scope difference is inferable from the 'report' framing here.

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 an explicit when: 'Use when someone asks whether their website is ready for AI agents, AI search, ChatGPT, Claude, Perplexity...'. It names likely trigger phrasings and the agentic-commerce case. It does not name the sibling explain_check or state when NOT to use this versus drilling into a single check, so it stops short of full routing guidance.

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