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

Annotations only supply destructiveHint=true; the description adds real behavioral context — billing stops, in-flight/future requests fail, and the state is recoverable via restart. It also discloses the underlying REST semantics (PATCH with state=STOPPED), which helps the agent predict idempotent behavior. It doesn't cover data retention or propagation timing.

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 what the tool does, then consequences, then API mapping. No filler, and each sentence adds a distinct fact.

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 one-parameter, no-output-schema mutation tool this is nearly complete: the agent knows the effect, the reversibility, and the failure mode of dependent calls. Minor gaps remain around whether stopping is immediate/synchronous and what the response looks like, but these are low-risk for a hint about a rich API.

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 description coverage is 100% for the single endpoint_id parameter, so the schema already carries the semantics. The description only echoes the id via the REST path notation, adding no new parameter meaning. Baseline 3 applies.

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: 'Stop a running dedicated endpoint.' Combined with the title and the sibling set, an agent can immediately distinguish this from together_start_endpoint, together_create_endpoint, or together_get_endpoint.

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 a clear condition for use (to stop per-minute billing) and states the operational consequence that requests fail until restarted, which implicitly points to together_start_endpoint as the reverse action. It stops short of explicitly naming the restart tool as the alternative.

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