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

Annotations already flag the write/idempotent/destructive profile, and the description adds genuinely new behavioral facts: the explicit confirm gate, the absence of any outbound send side effect despite email/text types, and the duplicate-accumulation risk from repeated calls. These are consequences an agent cannot derive from readOnlyHint/destructiveHint alone.

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?

Leads with the gating fact ('WRITE: Requires confirm:true'), then purpose, then the non-obvious caveat, then the endpoint. Four short clauses with no filler and the highest-risk information 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?

With 6 fully documented parameters, no output schema, and annotations covering the safety profile, the description is sufficient to call correctly. It does not say what the call returns (e.g. the new activity id), which matters slightly for a create tool whose result might be chained, but that is a minor gap.

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 100% and each parameter already carries a description, including the enum on 'type' and the guidance to use 'other' for a plain note. The description's 'a call, meeting, note...' only loosely gestures at the enum values, so it adds no semantics the schema does not already provide — baseline 3.

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 and resource ('log an activity ... on a candidate's record') and names the concrete subtypes (call, meeting, note). The trailing 'POST /candidates/{id}/activities' plus the fact that siblings like cats_list_candidate_activities are read tools makes the write/read distinction 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?

Gives a hard precondition ('Requires confirm:true') and an explicit exclusion — it will not send email/SMS even for type 'email' or 'text_message' — which is exactly the kind of guidance an agent needs before choosing it. It stops short of naming the read-side siblings (cats_list_candidate_activities, cats_list_activities) that an agent would use instead when logging is not the goal.

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