coldHat

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), and the description adds real behavioral value by disclosing exactly what is compared (hat code + seal vs. the hat as served now) and enumerating the full answer domain: verified, stale, cut-off, seal-missing, seal-wrong, pasted, not-worn. It stops short of explaining what a caller should do with each outcome.

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, front-loaded with the core check before the enumeration of outcomes; the outcome list is dense but each item earns its place. Minor jargon load ('hat code', 'seal') slows a first read but nothing is wasted.

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 correctly compensates by listing the possible verdicts, and the annotations cover safety and open-world behavior. What remains unstated is whether there is a cost/limit to checking, and how the caller should act on each verdict, so it is complete but not exhaustive.

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 two parameters are already documented, but the description adds meaning the schema does not: 'the hat as served now' clarifies that 'address' resolves to the live current hat, and 'the hat code and seal the reply quotes' explains the semantic link between the 'reply' string and the 'address'. That is genuine added context above the baseline 3.

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 ('Check') and resource ('whether a reply wore the current version of a hat'), and the mechanism (compares the quoted hat code and seal against the hat as served now) makes the operation concrete. It is distinguishable from wear_hat/wear_stack by being a read-only verification rather than a wearing action, though it never names those siblings explicitly.

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 framing implies you run this on a reply that quotes a hat, but there is no explicit when-to-use, no when-not-to-use, and no mention of the sibling tools wear_hat/wear_stack or how this fits after them. Guidance is left entirely 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 and openWorldHint, so safety is covered; the description goes beyond that by stating the fetched content and the ongoing obligation to 'follow the hat for the rest of the conversation, starting with the first reply it describes'. That persistent behavioral instruction is genuinely additive.

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?

It is compact and front-loads the fetch purpose before the invocation triggers and the follow-on behavior. The invented vocabulary ('coldHat', 'open sesame') costs some immediate parsing clarity, but every clause carries actionable information.

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 only two well-documented parameters, no output schema, and annotations covering the read-only/open-world profile, the description supplies what is missing: activation triggers and the post-fetch protocol. Nothing essential to correct invocation is absent.

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% and both parameters have inline descriptions (named hat vs main hat, GitHub user name with example), so the schema does the heavy lifting. The description mentions 'a name or a coldhat.f-keys.com/u/ address', which loosely maps to the user parameter but adds no 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?

The description gives a specific verb+resource ('Fetch a person's coldHat') and unpacks it as 'their working rules, voice and dated facts', so the agent knows what comes back. It does not name or differentiate itself from the siblings verify_hat or wear_stack, leaving that routing to inference.

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 states an explicit trigger: 'Call it when the user asks to put on a hat or says "open sesame" with a name or a coldhat.f-keys.com/u/ address'. That is clear activation context, but there is no when-not guidance or reference to the sibling tools for verification or stacked hats.

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=true, so the safety profile is covered. The description adds genuinely new behavior beyond the schema: a maximum of three stacked addresses and the instruction to carry the fetched result forward for the rest of the conversation. It still says nothing about error handling for malformed addresses.

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, front-loaded with the purpose before the trigger condition, and no filler. The quoted-mantra phrasing ("open sesame") is unusual but it is the literal trigger, so it 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 tool with no output schema, the definition covers what to pass, when to invoke, and what to do with the result. The one gap is that the return shape is never characterized, only that it should be "followed".

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 address parameter already carries the format and an example, so the schema does the heavy lifting. The description echoes the accepted prefixes and stacking but adds no syntax detail beyond what the schema provides, making the baseline 3 correct.

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 concrete verb and resource ("Fetch any coldHat address") and enumerates the address subtypes it accepts: a person's hat, a Fabric pattern, a prompts.chat prompt, or a stack. It does not, however, contrast itself with the sibling wear_hat or verify_hat, so the agent must infer why stacking goes to this tool rather than wear_hat.

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 invocation trigger (user says "open sesame" with a coldhat.f-keys.com address containing fabric/, prompts/ or +) plus a post-call instruction to follow the result for the rest of the conversation. It stops short of naming the alternatives (wear_hat, verify_hat) or stating when not to use this tool.

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