Ver mudanças observadas

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly reveals a critical side effect: calling the tool clears the accumulated events. It also discloses the dual-mode behavior (poll vs. list). This is strong, though it does not mention error conditions or response format, which are minor gaps for a simple poll tool.

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?

A single sentence that front-loads the primary action ('returns and clears accumulated events') and appends the alternative mode in parentheses. Zero wasted words, clear structure, and easy to scan.

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 simple tool with one optional parameter and no output schema, the description explains both execution modes and the key side effect. It does not describe the shape of returned events, but that is arguably discoverable from usage context. Given the tool's simplicity, this is sufficiently complete.

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 there is one optional parameter. The description fully compensates by explaining that providing watch_id polls that watch, while omitting it lists all watches. This adds meaning the schema alone lacks, making it clear how the parameter controls behavior.

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 a specific verb-resource pair: 'returns and clears accumulated events of a watch,' and also distinguishes the alternative behavior of listing watches when watch_id is omitted. This differentiates it from siblings like watch_start and watch_stop, which are lifecycle tools with different purposes.

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 implies usage by saying it returns and clears accumulated events, which logically follows watch_start, but it does not explicitly state 'use after watch_start' or contrast with watch_stop. It does give a clear conditional for the alternative behavior (omit watch_id), but no explicit when-not guidance.

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