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

Beyond the readOnly/idempotent annotations, it discloses the required 'Last Price' credential and a concrete failure mode: sandbox keys from self-registration get a 403 until a human claims the workspace. That is exactly the pre-call context an agent needs and would otherwise have to discover by failing.

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 compact sentences: what it returns and why, then the read-only boundary, then prerequisites. Purpose is front-loaded and no sentence is padding.

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?

With one fully described parameter, no output schema, and annotations covering safety, the description still names the returned metrics and the credential/workspace prerequisites. Nothing needed to call it correctly is missing.

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 the single 'model' parameter is already documented, so the schema carries the weight. The description only restates 'Pass the model name as model' without adding format or naming conventions.

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 latest profiling report') plus the exact payload ('measured latency, throughput and memory per backend') and the decision it supports. It also disambiguates from the run-starting sibling by saying 'Read-only; it does not start a run.'

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 use case ('so you can choose how to serve it') and an implicit exclusion of the alternative profiling tool ('it does not start a run'). It lacks an explicit pointer naming start_aitune_profiling as the tool to use when no report exists yet.

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