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

Annotations only declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds non-obvious behavior: the outcome must be verified before reporting, the server assigns agent identity and provenance, retries should reuse externalId without re-performing the underlying action, and the returned event ID must be captured before claiming completion.

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?

Front-loaded with the core purpose, then when-nots, then retry/provenance mechanics. Dense but nearly every clause carries operational information; only the final 'capture the returned event ID' sentence is arguably redundant with the output schema.

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?

An output schema exists, so return values need not be described, and the description appropriately defers to it while still flagging the event ID. It covers verification, dedup/retry, and exclusion criteria well, but provides no guidance on the 12 undocumented input fields, which is a real gap for a 14-parameter tool.

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 14 parameters, so the description must carry the semantic load. It enriches only url ('a real result URL') and externalId ('stable', reuse on retries), leaving verb, summary, category, status, system, value, currency, metadata, occurredAt, objectName/objectType completely unexplained.

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 states a specific verb and resource ('Record an external action you performed or attempted on the user's behalf'), names concrete categories of actions, and implicitly distinguishes itself from the read-only sibling by contrasting what to report vs. what not to (reads, research). An agent can identify the tool's role without opening the schema.

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?

Explicit when-to-use ('after verifying its actual outcome'), an enumerated list of qualifying action types, and an explicit when-not list ('Do not report reads, research, unsent drafts, local development, or the call to this tool'). This is about as unambiguous as usage guidance gets.

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