play_get_raw_error_reports

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 does not state whether the operation is read-only, whether pagination is involved (despite the page_size parameter), or what happens when the issue ID is invalid. The mention of 'multi-device environmental samples and full stack traces' gives some expectation of the data scope, but it omits critical behaviors like potential large payloads or the need for authentication. This is a significant gap for a data-fetching 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?

The description is a single sentence with a clear, front-loaded bracket tag. It conveys the tool's purpose and scope in under 20 words, with no filler. The structure is efficient and immediately actionable for an agent, and every word 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?

Given that there is no output schema, the description should explain what the tool returns and how the caller can use the response. It mentions 'environmental samples and full stack traces' but doesn't describe the response structure, pagination behavior, or error handling. The tool has three parameters (one required) and a specialized drill-down purpose, so the description gives the gist but leaves out details an agent might need to correctly parse the output. It's adequate but not 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?

The schema description coverage is 100%, so all three parameters are already documented. The tool description adds minimal value: it reiterates that 'issue_name' identifies the error and implies 'page_size' controls sample count, but it doesn't explain the exact format of 'issue_name' beyond the schema's example or clarify the default behavior of 'page_size'. Since the schema already covers parameter meaning, the description doesn't need to repeat it, but it also doesn't enrich the semantics beyond what's structured.

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 ('Fetch') and resource ('multi-device environmental samples and full stack traces for a specific error issue ID'). The 'Deep-dive Drilldown' prefix and the specificity of 'raw' set it apart from siblings like play_get_error_reports, which presumably returns aggregated data. An agent can immediately understand what this tool does and when it would be useful.

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 gives an implied usage context ('Deep-dive Drilldown') but does not explicitly state when to use this tool over alternatives like play_get_error_reports or play_search_error_issues. It doesn't provide exclusion criteria or mention that raw stack traces are only needed for deep investigation. The guidance is implicit rather than explicit, so it falls short of a clear routing instruction.

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