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

The annotation only carries destructiveHint=true, so the description does real work: it warns the endpoint STARTS AUTOMATICALLY and bills per minute of uptime until stopped. That is exactly the cost/behavioral fact an agent needs before invoking, and it does not contradict the annotation.

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 tight clauses, purpose front-loaded, the billing hazard emphasized, and the hardware-id pointer last. Nothing is redundant and there is no filler.

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 an 8-parameter creation tool with no output schema, the description covers cost behavior, the auto-start default, and the hardware lookup dependency. The one gap is that it never says what comes back (e.g. an endpoint id needed for later start/stop calls), which matters for a create-then-manage workflow.

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 already 88%, so the baseline is 3, but the description adds real meaning beyond the schema: inactive_timeout is framed as the auto-stop lever, hardware is tied to together_list_hardware for valid ids, and the automatic start is stated even though 'state' lives only in the 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?

States a specific verb and resource ('Deploy a model on dedicated GPUs'), which separates it cleanly from together_start_endpoint, together_stop_endpoint, and together_list_endpoints. The 'POST /endpoints' note pins down the underlying resource so the agent knows exactly what is being created.

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 concrete routing guidance ('use together_list_hardware for valid hardware ids') and conditional advice ('set inactive_timeout to auto-stop it'), which tells the agent what to do before and after calling. It stops short of explicitly contrasting this with alternatives like start_endpoint or serverless chat_completion, so it is clear context rather than full 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.