Annotate Metric

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

With no annotations provided, the description carries the full burden and does reasonably well: it discloses that this mutates data, states the write-permission prerequisite, and offers a dry_run escape hatch. It omits other behavioral traits an agent would want, such as whether annotations are additive/duplicative, how errors on an unknown metric or period are surfaced, and how severity affects the record.

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?

Two tight, front-loaded blocks — purpose first, then the effect/dry-run contract — with no filler sentences. 'Durable' is doing light work but the rest earns its place.

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 six-parameter mutation tool with 0% schema coverage and no annotations or output schema, the definition covers write semantics and previewing but leaves the core parameter vocabulary (metric identifier, period format, severity scale) undefined, so an agent could still call it incorrectly.

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 six parameters, so the description must compensate and largely does not. Only dry_run is explained; the formats of metric, period, note, author, and the allowed severity values remain unspecified in both schema and prose.

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 (attach) and resource (a durable finding/note/root-cause explanation) scoped to a KPI metric and recording period, which is concrete enough to separate it from read-oriented siblings like query_kpis or list_annotations. It stops short of explicitly naming the inverse sibling retract_annotation, so sibling disambiguation is only implied by the word 'durable'.

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 real operational context: write permissions must be enabled, and dry_run=true previews without committing. However it never states when this tool is the right choice versus list_annotations/retract_annotation, nor when not to use it, leaving usage largely inferred.

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