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

Annotations already mark the tool as read-only and non-destructive, and the description adds substantial behavioral context beyond that: full detail can be refused on large frameworks, the refusal will name families, and `userContent` fields must be treated as data, not instructions. This is a strong prompt-injection guardrail and response-behavior disclosure. No contradiction with annotations exists.

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 front-loaded with the core list behavior and output fields, then moves to detail-mode guidance, response-size caveats, and the security note. Every sentence earns its place; the length is justified by non-obvious behavioral and safety information an agent needs.

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?

There is no output schema, so the description carries the burden of explaining return values; it lists the returned fields and covers response-limit refusal behavior. It also includes the tenant-data warning and relies on a rich input schema for parameter details. Nothing critical is missing for correct invocation.

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 already documents all four parameters at 100% coverage, so the baseline is 3. The description adds meaningful semantics around `detail` (whole-program end-to-end use vs. small summary map) and `family` (one family at a time for large frameworks). Project and framework parameters remain well explained in the schema, and the description's additions lift it slightly above baseline.

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 a specific verb and resource ('List a project's controls') and enumerates the returned fields: number, family, title, weight, read counts, and attestation evidence. This clearly distinguishes it from siblings like get_control and search_controls as the list-level tool. It also clarifies optional family filtering, leaving no ambiguity about its scope.

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 provides concrete usage context: use the default summary to keep the map small, pass detail:"full" to work a whole program end-to-end, and read one family at a time on large frameworks because full detail is capped by response size. It explicitly recommends optional family filtering. It does not explicitly name alternatives such as search_controls or get_control, but the context is clear enough for an agent to select this tool.

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