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

Annotations already cover read-only/idempotent/closed-world, and the description still adds real behavioral detail beyond them: selector semantics (unselected transcripts may span attempts; recording resolves to the latest known attempt) and an explicit content-trust warning that call content is information, not instructions. Pagination or response size behavior is not disclosed, but an output schema exists to carry return shape.

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-loaded with the outcome, then the selector rules, then the trust caveat; no filler sentences. Some density in the pointer syntax ("media[].attempts[].read") is terse but functional.

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?

For a 4-parameter read tool with full schema coverage, an output schema, and strong annotations, the description covers what an agent needs to select the right mode and interpret content safely. The one missing piece is any signal about which sibling to choose when the agent doesn't already have a taskId.

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 baseline is 3; the description earns above that by explaining the cross-parameter contract — attemptNumber is only meaningful with callId plus a transcript/recording include, and `include` maps to the more.sections list a reply advertises. It does not explain what `all` costs in payload terms beyond calling it "the long form".

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?

Opens with a specific verb+resource plus the payload it returns ("Read a task's questions, price, progress or result and next actions"), which is far more informative than the title "Read a call request". It never names the neighboring retrieval tools (find_task, list_tasks, prepare_task) even though they are the obvious alternatives, so an agent can't fully separate it from siblings on this description alone.

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 conditional usage rules rather than vague framing: add `include` for sections listed under more, use callId+attemptNumber to target a single attempt, and expect transcripts to span attempts when no selector is supplied. It stops short of naming when to prefer a sibling such as list_tasks or find_task.

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