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

Annotations already flag destructiveHint=true and non-idempotent, and the description adds substantial context beyond them: partial-update semantics (omitted fields retained), the null/[] clearing behavior for specific fields, that changes take effect on the agent's next model call, and the critical failure mode where narrowing below an agent config breaks its next call. This is exactly the behavioral disclosure an agent cannot infer from structured fields.

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?

The core purpose is front-loaded, followed by three dense, non-redundant sentences covering clearing semantics, propagation timing, and the failure mode. Every sentence earns its place with 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 a 13-param mutation tool with no output schema, the description covers the behaviorally important edge cases: partial update, override clearing, propagation timing, and validation/failure scope. Annotations carry the safety profile, so nothing essential to correct invocation 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 92%, so the baseline is 3, but the description adds meaning the schema lacks: which specific parameters support null/[] clearing (supported_reasoning_efforts, input_modalities, output_modalities) and that omission preserves current values. It does not cover the remaining params, but the added clearing semantics are the high-value ones.

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: updating the project's overrides for the configured model. The grant_models_* siblings (add/delete/list) are clearly differentiated by the 'overrides' framing, so an agent can pick this tool 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?

Explains the operational contract for omitted vs null vs [] values, which is effectively guidance on how to invoke it correctly. It does not, however, explicitly name when to prefer this over grant_models_add/delete or state exclusions, so it falls short of full when/when-not routing.

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