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

Annotations only supply readOnlyHint=false and destructiveHint=false. The description adds substantial behavior: partial-update semantics ('Only the fields sent are touched'), a hard authorization gate (money-spending facts refused without an approved training_spend record), spend clamping to an approved cap, and monotonic constraints ('status and cleanup only move forward'). That is far more than the annotations convey.

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 field vocabulary, then constrained behaviors, then scope. Dense and mostly earned, though the middle sentence packing authorization, cap-binding and monotonicity into one run-on reduces scannability.

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?

Covers the essentials an agent needs for a partial-write tool: mutation semantics, auth gate, scope restriction, and non-settable fields. It says nothing about the response (no output schema exists), so error/return behavior is left unspecified.

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?

With only 56% schema description coverage, the description compensates by explaining the semantics of the money-related params (spend bound to cap, provider/serving refs gated) and the direction constraint on status/endpointCleanup. It leaves several parameters (customerId, receipts merge is only in schema) without added meaning, so it does not fully close the coverage gap.

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 ('Report a job's independent facts') and enumerates exactly which fact groups it covers: status, endpoint cleanup, spend, servable model id, provider job ref, receipts. It does not name the sibling it differs from (e.g. record_training_job / get_training_job), so it stops short of full sibling differentiation.

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 clear callability context ('For the training runner's key... write, admin and superadmin keys cannot call it') and states an exclusion ('The gate outcome is not settable here'), which steers the agent away from using this for gate results. It does not explicitly name the alternative tool for those cases.

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