record_change

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the bar is lower; the description adds that `at_iso` defaults to now, which explains the temporal behaviour. However it does not disclose what happens on a duplicate recording (idempotentHint=false suggests new records are appended, but that is left for the agent to infer), nor that unknown `kind` values are apparently unsupported despite the schema accepting any string.

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 zero filler; the kind-first structure means the agent learns the discriminator before the per-kind fields. The parenthetical enumeration is dense but readable. Only minor cost: the reader must parse nested parentheses to extract which fields belong to which kind.

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 9-parameter mutation tool with 0% schema description coverage and no output schema, this is roughly adequate but not sufficient: the required `author` and the optional `note` are undocumented, and nothing is said about the return value or whether the record is visible to recent_changes afterwards. It covers the discriminating parameters well but leaves the mandatory identity field unexplained.

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%, so the description must carry the load, and it does most of it: it maps the deploy fields (service, version, prev_version) and flag fields (flag, enabled) to their respective kinds and specifies `at_iso` as ISO 8601 defaulting to now. It omits the required `author` parameter entirely and never mentions `note`, which is a real gap given that author is one of only two required fields, costing a point.

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 (Record) plus the two discriminated resource shapes: a deploy (service, version, prev_version) and a flag flip (flag, enabled). An agent can distinguish it from read-only siblings like recent_changes or get_logs, though it never names a sibling explicitly. The kind-discriminated field grouping is precise enough to guide the call.

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?

Usage is only implied — the description tells you which kind to pick for a deploy vs a flag flip, which is real intra-tool routing guidance. But it never says when to record a change versus simply reading recent_changes, nor whether this is for changes you performed or changes observed in an incident timeline. No prerequisites or exclusions are stated.

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