compute.reconcile_storage_plan

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

Annotations only give readOnlyHint=false, so the description carries most of the weight and does so usefully: it discloses that the plan becomes 'superseded', that guards are released, and critically that the operation does not resume or continue deletion. It still doesn't say whether the closing is reversible, what happens to resources already created by the plan, or whether the call fails if approval is stale.

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?

Three short, front-loaded sentences with no padding, and the safety-critical constraint is repeated at the end where it will be noticed. The only weak spot is the vague lead-in about observing the manifest, which spends words without adding precision.

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 two-parameter mutation with no output schema and only a readOnlyHint, the description covers the essential behavioral facts: what is mutated, that guards are released, that deletion is not resumed, and that human approval plus confirm=true is mandatory. Gaps remain around return value and what happens to downstream resources, but nothing required to call it safely 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 0% and neither parameter is described in the schema, so the description must compensate. It clarifies the 'confirm' parameter (must be true and backed by fresh human approval), which is real added value, but leaves 'plan_id' unexplained - it never says whether it identifies the old plan to supersede or the plan whose manifest is observed.

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+object: close an old storage plan as superseded and release its guards, which is concrete and distinguishes it from a generic delete or apply. However, the opening phrase 'observe the stored manifest' is undefined jargon that muddies what the tool actually reads versus mutates, and no sibling (e.g. compute_apply_storage_plan, compute_get_storage_plan) is named to sharpen the distinction.

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?

Provides negative guidance ('never continues deletion or resumes the plan') and a precondition ('requires fresh human approval and confirm=true'), which helps. It does not state positively when an agent should call this versus compute_apply_storage_plan or compute_get_storage_plan, so the routing decision 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.