agent_tool_contract

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, and the description is consistent with them (a design/advice operation), so there is no contradiction. However, the description adds no behavioral context of its own — nothing about whether output is deterministic for identical inputs, whether it validates or critiques an existing contract, or any constraints beyond the schema.

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?

A single front-loaded sentence with no filler or redundancy. It is efficient, though the efficiency comes partly from omitting rather than compressing necessary detail.

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?

The presence of an output schema means return values need not be explained, which the description correctly leaves out. But for a tool with five mandatory, undescribed inputs and no usage routing, the definition is thin — it never says what the resulting contract contains or how the inputs shape it, leaving the agent to guess at semantics.

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 description coverage is 0% across five required parameters, so the description carries the full burden and largely fails: 'per-operation' faintly hints at 'operation', 'authorization' at 'approvalRequired', and 'recovery' at 'reversible', but 'resourceScope' (array of strings, up to 30 items) and 'maxDurationSeconds' (1–3600) get no explanation at all. An agent cannot tell what a valid scope entry looks like or how the duration bound should be chosen.

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 ('Design') and a specific artifact ('per-operation authorization and recovery contract for an agent tool'), which is distinguishable from siblings such as agent_eval_plan or implementation_plan. The word 'contract' is left abstract, so the agent gets the category but not the shape of the deliverable.

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?

There is no statement of when to reach for this tool versus agent_eval_plan, implementation_plan, or threat_model, and no prerequisites or exclusions are given. The agent must infer timing entirely from the one-line purpose.

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