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

Annotations already declare readOnly, idempotent and non-destructive. The description adds genuinely new behavioral facts beyond them: the call is free, it starts nothing, and the answer is only available once saved, which explains why repeated polling may still return 'running'.

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 tight sentence plus a short clarifying fragment; the operation and its precondition are front-loaded and nothing is repeated from the schema or annotations.

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 three-parameter polling read with an output schema, the description covers purpose, precondition, cost and the 'running' result semantics. Only polling cadence and a terminal failure state are left unstated, which are minor gaps.

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, but the description goes further by telling the agent that surveyId, threadId and afterMessageId all come from the skill_run call, and that afterMessageId only exists when skill_run returned one. That provenance is meaning the schema does not convey.

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?

States a specific verb and resource ('Read the answer of a skill run') with the qualifying condition that the run returned status 'running'. The phrase 'Free: it starts nothing' implicitly separates it from the sibling skill_run, which does start work, though no sibling is named explicitly.

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 condition for use is clear: call it for a skill run that already returned 'running'. 'Returns status running until the answer is saved' implies the polling loop, but the description never says how often to re-poll or when to stop trying, and no alternative is named.

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