rec_stats

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

With readOnlyHint/destructiveHint already supplied by annotations, the description adds real behavioral context: statistics are 'computed incrementally, no re-read of the file,' and scope is 'the whole recording so far.' This tells the agent about update semantics and cost that the annotations do not cover.

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 dense, front-loaded sentence that opens with the core concept ('Per-symbol statistics over the whole recording so far') and enumerates outputs efficiently. The em-dash appositive makes it long 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?

An output schema exists, so return values needn't be detailed, and the read-only annotations cover the safety profile. The description explains the analytical content well; the main gap is that four undocumented parameters get no explanation.

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% across four parameters (id, symbols, max_runs, include_runs). The description implies 'per-symbol' selection and 'value runs' (loosely mapping to include_runs/max_runs) but never explains id, the symbols selector, or the max_runs=200 cap, leaving most parameter meaning undocumented.

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?

It states a specific verb+resource: computing per-symbol statistics (count, min/max/mean, edges, runs) over the whole recording. This clearly distinguishes it from raw-read siblings like rec_read/rec_snapshot, but it never names an alternative explicitly, so it stops short of full sibling differentiation.

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?

There is no explicit when-to-use/when-not guidance or mention of alternatives such as rec_read or rec_pulses. Usage is only implied by the fact that it reports analytical aggregates rather than raw samples.

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