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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's real contribution is 'What it found so far is kept' — a substantive reassurance that stopping is not data loss, which no structured field conveys. It doesn't address error behavior when no run exists, which keeps it from a 5.

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 short sentences, front-loaded with the action and scope, then the key behavioral fact, then the usage constraint. Nothing is padded and each sentence carries distinct information.

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 two-parameter mutation with no output schema and rich annotations, the description covers what it does, what is preserved, and when to invoke it. A pointer to how to retrieve partial results afterward (get_research_run) would close the remaining gap.

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% and both parameters are fully documented in the schema, including the UUID retry semantics for clientRequestId. The description's parenthetical '(projectId)' merely echoes the schema, adding no syntax or sourcing detail beyond it.

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?

Specific verb ('Stops') plus a precise resource and scope ('the run in progress on one of the member's projects'), with the required identifier named inline. An agent can immediately tell this apart from archive_research_project (project-level), start_research_run (the inverse), and get_research_run (a read).

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?

'Call it only when the member asked to stop it' gives an explicit gating condition that prevents an agent from stopping runs unprompted. It stops short of naming alternatives or describing the case where no run is in progress, so it is clear context rather than complete when/when-not guidance.

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