ColdRead

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds the useful guarantee that it 'never pays' a seller and that the call is free, which matters when the surrounding workflow is payment-related. It also discloses the ~28 h scoring window and that the output is signed. It does not say what happens on a failed/unreachable endpoint or how expensive the check is in latency.

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 decision cue is front-loaded in the first clause, followed by the evidence bundle, then two clipped sentences on read-only/no-pay and cost. Dense but every clause carries information an agent needs before spending a call.

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 the report contents, and it does so by enumerating the constituent checks and the time window. Remaining gaps are how the report is returned (inline vs. an ID for coldread_get_report) and failure behaviour, which an agent would want given the sibling get/verify tools.

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 schema already documents url, agent, method, and pay_to, including the 'auto tries both' semantics and the pay_to mismatch guidance. The description adds context that an ERC-8004 identity lookup and payer summary are performed, but gives no extra detail on method or pay_to handling. 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?

The description names a concrete verb class (produce a signed, independent report) and enumerates the checks it bundles: 402-challenge lint, signed-offer/signer authorization, ERC-8004 lookup, and a Base USDC payer summary. That is far more specific than the title 'ColdRead check'. It does not, however, distinguish itself from coldread_get_report or coldread_verify_report, so an agent still has to infer this is the one that runs the check rather than fetch or validate an existing report.

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?

'Before paying an x402 seller' supplies a clear triggering condition and timing, which is exactly the decision point an agent needs. There are no explicit when-not conditions and no named alternatives among the sibling tools, 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.

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

readOnlyHint=true already tells the agent this is a safe read, and the description adds useful context that reports are signed and retained only 90 days. It omits what happens on an expired or unknown digest (error vs empty), which matters for a digest-keyed lookup.

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?

One sentence, front-loaded with the action and keyed resource, with the retention constraint appended. Nothing is 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?

For a single-param read tool with annotations covering safety, the description covers what is fetched and the retention window. The only real gap is expected failure behavior for expired/missing digests, which is minor here.

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 0% and the single param is just typed string, so the description carries the burden; saying 'sha256 digest' tells the agent the expected format, which the schema does not. It could still clarify encoding (hex) and length.

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 ('Fetch a stored signed report') plus the lookup key ('by its sha256 digest'), so an agent knows exactly what it does. It does not differentiate from the sibling coldread_verify_report, which is a real ambiguity given both operate on signed reports.

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: call this when you already hold a digest. The 90-day retention note hints at a precondition, but there is no explicit guidance on when to use this versus coldread_verify_report or coldread_check.

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?

readOnlyHint=true is consistent with a verification operation, so the safety bar is already met and no contradiction exists. The description adds real mechanism (JCS + sha256, signature against a published key), but says nothing about outcome behavior: whether a failed check raises an error or returns a falsy result, what happens with an untrusted/unpublished key, or whether network/key-lookup is involved.

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, with the core semantic (what is verified) front-loaded and the input requirement second. Every clause carries information an agent needs.

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?

There is no output schema, so the description is the only place a caller could learn that this returns a pass/fail verdict, an error reason, or the key identity used — and it does not. For a trust/security tool where the caller must act on the result, that omission matters, though the input side is adequately covered.

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 0% and the single parameter is an opaque nested object, so the schema alone tells an agent nothing. The description compensates by enumerating the envelope's required shape as {report, digest, signature}, which is genuinely additive. It stops short of describing encodings or formats for digest and signature, which remain ambiguous.

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+resource (verify a ColdRead report envelope) and specifies the exact check performed: JCS canonicalization + sha256 integrity plus signature against a published ColdRead key. An agent knows precisely what this tool does, but the description never differentiates it from the sibling 'coldread_check', which by name sounds like the same activity.

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 only guidance is 'Pass the whole envelope {report, digest, signature}', which is input-formatting advice rather than a when-to-use rule. With siblings 'coldread_check' and 'coldread_get_report' present, the description gives no condition for choosing this tool over them and no preconditions (e.g., must the report have been fetched first?).

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