Update check

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

Annotations already mark the tool as non-readOnly, idempotent, and destructive, so the bar is lower. The description adds valuable behavioral context beyond those annotations: partial-update semantics, channels replacing the integration list rather than merging, and schedule taking precedence over timeout. It also discloses the UUID/read-only key limitation. The 'destructiveHint: true' is consistent with the replace-not-merge and schedule-switch behavior described. Minor gap: it doesn't explicitly state whether the update is irreversible or what happens to downstream pings, but the description is honest and substantial.

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 sentences, each earning its place: the first states the core behavior and partial-update default, the second flags the two counterintuitive exceptions, the third warns about UUID visibility for read-only keys. Information-dense with zero filler and the most important caveats front-loaded.

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?

Given 19 parameters, a 100%-covered schema, an output schema, and annotations covering read-only/destructive/idempotence, the description covers the gaps that structured data cannot: partial-update semantics, replace-vs-merge, schedule-vs-timeout precedence, and the UUID/read-only-key constraint. It does not spell out that an empty payload is pointless or that channels with an empty list is refused, but the schema's required 'check' field and the channels description already handle those. Very complete for the tool's 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 description coverage is 100%, so the schema already documents all 19 parameters thoroughly with ranges, patterns, and mutual exclusions. The description adds cross-cutting semantics that the schema can't: the partial-update default ('Fields that are not given stay unchanged') and the two exceptions (channels replaces, schedule overrides timeout). That is genuinely useful but the heavy lifting is done by the schema, so baseline 3 is appropriate.

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?

The description clearly states 'Updates a check' with a specific verb and resource, and immediately clarifies partial-update semantics ('Fields that are not given stay unchanged'). It doesn't explicitly differentiate from sibling tools like create_check, pause_check, or resume_check, but the name and verb make the core purpose unambiguous.

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 description gives implicit but clear usage context: it is a partial update operation, and it flags the two non-obvious behavioral exceptions (channels replaces rather than merges; schedule overrides timeout) that an agent must know before calling. It does not explicitly say 'use create_check to create a new check' or 'use pause_check to pause', but the exceptions serve as important when-to-call guidance for this tool versus alternatives. A slightly explicit alternative comparison would push this to 5.

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