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

Annotations already declare readOnlyHint=false (write) and destructiveHint=false, and the description reinforces this with 'Scope: write' while adding the non-obvious fact that it 'Executes nothing and decides nothing.' That workflow clarification (request queues for decide_approval) is real added value beyond the safety hints, though it stops short of describing the resulting approval state.

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?

Two dense sentences that front-load the purpose and then the per-scope conditions with no filler. It is information-heavy rather than wasteful, though the second sentence packs several constraints that reward careful reading.

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 no output schema, the description covers the essentials: the two scopes, their prerequisites, the write/does-not-execute behavior, and the handoff to decide_approval. It is nearly complete for a mutation tool whose annotations already carry the safety profile.

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 83%, so the baseline is 3, but the description adds genuine meaning: the capUsd 'must equal the job's own cap' constraint and the conditional logic that jobId is taken for production_switch only when more than one candidate qualifies. These rules are not evident from the schema alone.

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+resource ('Ask for one of the two fine-tuning approvals') and explicitly distinguishes itself from the sibling decide_approval by noting it 'decides nothing' and waits for that tool. An agent can tell immediately what this tool does versus its closest neighbor.

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 conditions for each of the two scopes: training_spend needs a job plus a cap equal to the job's own cap; production_switch needs a passing protected gate verdict and a servable model, with jobId only when multiple candidates qualify. Names the downstream alternative (decide_approval) and frames this tool as the request step in the flow.

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