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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: result ordering, the exact fields returned, an API-key scope requirement ('runs:read'), and truncation behavior via limit. Only edge behavior such as what happens when more than 100 runs exist is unaddressed.

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?

Three dense sentences with no filler: purpose and return fields first, then the auth requirement, then the routing alternative and the limit. The most decision-relevant information is front-loaded.

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 correctly compensates by listing the returned fields, and it covers auth scope and the limit. It is nearly complete for a simple read tool, with only the beyond-limit/pagination story left implicit.

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?

There is one parameter and the schema already carries its default (50), minimum (1) and maximum (100), so the description's restatement of default and max adds no meaning beyond the structured field. It does not explain what happens when the cap is reached or how to retrieve entries beyond 100.

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 opens with a specific verb and resource ('Lists the user's analyses (runs)'), states ordering ('newest first'), and enumerates the returned fields. It is clearly distinguishable from qualitative_get_run, which is named as the single-run alternative.

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?

It gives an explicit use case ('find a run_id when the user refers to earlier work') and an explicit routing rule away from it ('For the progress or details of one analysis use qualitative_get_run'). Both the when and the when-not are present.

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