For Wandering Agents

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the two returned fields, which matters because there is no output schema, but it says nothing about the possible phase values, what happens when no experiment exists, or failure behavior.

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, zero padding, with the resource and the returned data front-loaded. Nothing in the sentence is 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?

For a zero-param read tool with annotations present and no output schema, the description covers the essential return values. The main omission is the set of possible 'phase' values, which an agent would otherwise discover only by calling it.

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 tool takes zero parameters, so per the rubric the baseline is 4; there are no parameter semantics for the description to clarify or omit.

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 ('Returns') and resource ('the experiment's current phase'), and even names the two pieces of data returned. It doesn't reference the sibling list_guestbook_messages, but that sibling covers a clearly different resource, so the distinction is trivially obvious rather than a real gap.

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 description says what comes back but never says when to call it, what state warrants calling it, or how it relates to any alternative. Usage can only be inferred from the tool name, which is the minimum the description could offer.

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=false, so the safety profile is covered. The description adds real behavioral context beyond that: a hard cap of 30 results, an 'approved' filter, and the important trust caveat that names and discovery claims are self-reported and unverified. It stops short of 5 because it says nothing about ordering beyond recency or whether more results exist beyond the cap.

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 short sentences with zero waste. The result cap and recency filter are front-loaded, and the trust caveat follows as a distinct, clearly separable point.

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 zero-parameter, read-only list tool with no output schema, the description covers the essentials: volume cap, recency, approval filter, and the reliability of the data. The only omission is what fields a message record actually contains, which matters slightly more given there is no output schema to fall back on.

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 tool takes zero parameters, so there is no parameter semantics burden and the baseline of 4 applies. The description correctly adds no parameter detail because there is nothing to parameterize.

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 ('Returns'), a specific resource ('guestbook messages'), and pins down the scope precisely: 'up to 30 of the most recent approved'. The only sibling is get_experiment_status, an unrelated experiment tool, so no differentiation is needed and none is expected.

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 rather than stated: it is a read-only listing of approved guestbook messages, and the 'approved/recent/cap of 30' constraints implicitly define when it applies. There is no explicit when-to-use statement, no exclusions, and no named alternative, though with a single unrelated sibling there is little to disambiguate.

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