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

Annotations already establish readOnly, idempotent, non-destructive, so the description does not need to restate safety. It adds output behavior by saying it 'flag[s] single-point overfit risk' and ties the analysis to a specific protocolId. It does not disclose return shape or stability criteria, but the annotations cover the safety profile and the description gives a reasonable behavioral summary.

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, front-loaded with the verb and object and no filler. It could carry more detail, but it is efficiently structured.

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 the tool's complexity (25 parameters, no output schema, low schema coverage), a one-line summary is not enough for an agent to know expected return values, what 'stability' means, how overfit risk is determined, or what prior workflow steps are required. The description would need at least prerequisites, output semantics, and guidance across the analysis siblings to be 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 description coverage is only 24%, so the prose needs to compensate for 25 parameters; the only parameter it calls out is protocolId, and it merely labels it 'required' without adding semantics beyond the schema's own protocolId description. Required params like symbol, timeframe, startDate, endDate, and source are left entirely to the schema, so the description adds little to parameter understanding.

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 uses the specific action 'Summarize' with a clear resource ('parameter-sweep stability') and names the required protocolId input. It is clear enough to differentiate from running a sweep, but it never refers to sibling analysis tools such as analyze_overfit_probability or analyze_bootstrap_confidence, so sibling differentiation is only implicit.

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 the tool is used when a protocolId exists and the user wants a stability/overfit summary, but it gives no explicit when-to-use guidance, prerequisites (e.g., run_parameter_sweep must have completed), or exclusions. No alternative tools are mentioned, so an agent would have to infer when this is preferable to analyze_overfit_probability or stress_test_candidate.

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