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

Annotations already declare the tool read-only, idempotent, and non-destructive; the description adds meaningful behavioral context beyond that: it mandates exact headings/labels, requires each returned action to be shown exactly once, restricts action fields to those supplied, and prohibits opening pending links without approval. This gives an agent concrete rendering and safety behavior, though it does not cover error or rate-limit behavior.

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 purpose, then progressively adds rendering rules and safety constraints. No sentence is filler: the provider-neutral labeling rule, the actions-rendering rule, the field restriction, and the link-approval rule each add distinct value.

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 annotations cover the safety/idempotence profile and an output schema exists for return values, the description supplies the remaining necessary context: exact presentation requirements and a safety prohibition on opening pending links. An agent has enough information to invoke and render the tool correctly.

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 single top-level parameter `request` has no schema description (0% coverage), and the tool description does not compensate by explaining its subfields such as `question`, `caller`, `answer_mode`, or `max_sources`. The nested schema definitions provide some detail, but the description adds essentially no parameter-level meaning, leaving a real gap for a low-coverage schema.

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 action ('Ask a configured partner expert') and a clear output ('a citeable answer from approved sources'), so an agent knows what the tool produces. It references ask_expert and adds provider-neutral presentation rules, but it does not explicitly state how tat_ask differs from the sibling ask_expert, 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 usage: it should be used when a citeable answer from approved sources is needed and when provider-neutral source/confidence labeling is required. It does not state when not to use it or name an alternative for other answer styles, so the guidance is implied rather than explicit.

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