analysis_capture

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

Goes well past the annotations: it discloses the significant side effect that playback starts if stopped (explaining readOnlyHint=false), that the call is asynchronous and returns a job id rather than results, and that only one capture may run at once. These are exactly the traits an agent needs before invoking a non-readonly, non-idempotent 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?

Front-loads the action, then the payload, then the async contract and the concurrency caveat. The metric enumeration is a long semicolon chain, but with no output schema each listed field is genuinely informative rather than 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?

With no output schema, the description is the only documentation of what comes back, and it delivers that alongside the async retrieval path, the playback side effect, and the single-capture constraint. An agent can select and invoke it correctly from this text alone.

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 100%, so the schema already documents source, seconds and start_transport. The description restates the default duration and 1-30 range and clarifies 'master or one track', but adds no syntax or semantics beyond the structured fields.

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 and resource: capture what the master or one track plays and analyze it. The scope (live transport vs. offline file) implicitly distinguishes it from analysis_file and analysis_compare, and the enumerated metrics make clear exactly what kind of analysis this is.

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?

Gives a clear operating context (live capture, kicks playback if stopped) and an explicit follow-up path: 'Returns a job id at once: call jobs.wait with it.' It also states the concurrency rule 'One capture at a time.' It does not explicitly say when to prefer this over analysis_file or analysis_compare for a rendered file, so no exclusion clause.

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