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

With no annotations, the description carries the full burden and does: it discloses the cost/duplication hazard of re-running, the async lifecycle (study keeps running after a timeout or recoverable error), the recommended polling cadence, and the status state machine. It also warns which error shapes are recoverable.

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?

Front-loaded with the core purpose, then the failure-recovery path, then the return shape. Dense but every sentence carries operational information; no filler or restatement of the name.

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?

No output schema exists, yet the description compensates by describing the return shape ('same shape as the run tool that started it, plus a top-level status' with enumerated values). For a single-parameter read tool this leaves nothing an agent needs unstated.

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 100%, so the baseline would be 3, but the description adds real meaning by explaining that sim_id can come either from a run tool's success response or from the sim_id field of a recoverable error — context the schema only states tersely.

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?

Opens with a specific verb+resource+key ('Fetch the results of a study you ran, by id') and immediately scopes it as a retrieval-only operation, which cleanly separates it from the run_* siblings that launch studies. An agent can tell what it returns without opening the schema.

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 explicit when-to-use cases (read a study again, recover a run whose tool call failed), an explicit prohibition with the reason ('Do NOT re-run the tool — that launches and charges a second study'), and a concrete recovery procedure (wait 30-60s, call get_simulation(sim_id), poll while status is 'running'). Nothing is left to inference.

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