FRESH — Shared URL Freshness Intelligence

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering safety. The description adds the return value semantics but does not explain decision logic (e.g., what UNKNOWN means or how toleranceSeconds affects the result). This is useful but limited beyond annotation coverage.

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 a single sentence that front-loads the key output values and the usage context. Every word earns its place; there is no redundancy or filler.

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?

While the tool is simple and annotations cover safety, the description omits details about parameter semantics and decision criteria. No output schema exists, so the description must convey return behavior, which it partially does. However, the lack of parameter explanations and the vague UNKNOWN state make it incomplete for full understanding.

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 0%, yet the description provides no parameter explanations. The parameter names (url, lastSeenAt, toleranceSeconds) are somewhat self-explanatory, but the description fails to clarify their roles or how they interrelate, especially for required parameters.

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 states the tool's purpose with a specific verb ('Return') and explicit output values (REUSE, REFETCH, or UNKNOWN). It positions the tool as a pre-fetch check, distinguishing it from the sibling tool fresh_observe, which likely performs the actual observation.

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 phrase 'before retrieving a URL again' provides clear contextual guidance on when to use this tool. It does not explicitly mention alternatives, but the sibling relationship to fresh_observe makes the intended usage apparent. No exclusions are stated, but the context is sufficient.

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?

The annotations already provide some behavioral hints (readOnlyHint=false, openWorldHint=true, etc.). The description adds the note 'privacy-safe', which gives some context about data handling, but does not disclose other behavioral traits such as side effects (e.g., recording an observation) or whether repeated calls create duplicates, which might be expected given idempotentHint=false.

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 a single, front-loaded sentence that is entirely relevant. Every word contributes meaning, and there is no unnecessary repetition or filler.

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?

Given the tool's simplicity (5 params, no output schema), the description is adequate but leaves gaps. It does not explicitly state that this tool should be called after a retrieval (only implies it), nor does it explain what the tool returns (if anything) or provide context about the observation lifecycle. The lack of an output schema makes some return-value guidance valuable, but the description is sufficient for a basic understanding.

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 has 5 parameters with 0% description coverage, and the tool description does not explain individual parameters. The only hint is 'freshness metadata', which loosely connects to etag, lastModified, and contentHash, but it does not clarify formats, optionality, or interplay between fields. For a tool with moderate parameter count, the description fails to compensate for the schema's lack of descriptions.

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 states the verb 'Report' and the resource 'privacy-safe freshness metadata from a completed retrieval,' which conveys the tool's function. It implies this tool is for recording observations after a retrieval, distinguishing it from the sibling 'fresh_check' (which likely checks freshness), though it does not explicitly name 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?

The phrase 'from a completed retrieval' implicitly guides when to use this tool (after fetching a URL), but it does not explicitly state when NOT to use it or name the alternative tool 'fresh_check'. The usage context is implied rather than explicitly stated.

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