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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds real context beyond them: 'Resets its result and retains history' tells the agent state is destroyed yet auditable, and the final sentence clarifies the operation's blast radius. It omits any mention of idempotency_key semantics even though an idempotency_key parameter exists.

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 sentences, front-loaded with the action and followed by the state-effects and boundary caveats. Each sentence carries information, though the reasoning behind 'custom_' prefixing could be slightly clearer.

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 destructive, open-world write tool with no output schema and a nested definition object, the description covers state semantics but leaves out what a caller receives back after the reset, how expected_version conflicts are surfaced, and when to reuse idempotency_key. Adequate but not complete for a mutation of this complexity.

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 57%, and the schema self-documents company, environment, expected_version and idempotency_key. The description contributes only indirectly, implying the notes field is a required 'reason' and that the new capability must carry a 'custom_' prefix — a naming convention not stated anywhere in the schema. The nested definition object's seven fields get no description-level explanation.

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?

Names a specific action pair (edit an expectation / add a custom_ capability), identifies the resource, and adds a scope qualifier that rules out adjacent operations. It is clear against siblings like summer_capability_checks_get/list/test, though it never names one explicitly.

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?

The negative guidance ('Does not create a provider tool or grant execution access') usefully bounds what this is not, but there is no positive when-to-use statement, no mention of when to prefer this over summer_capability_checks_test or _report, and no concurrency/version-conflict guidance despite expected_version being required.

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