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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: internal-only visibility, no outbound delivery, and the concrete semantics of a repeat call ('a repeat returns the original note'). It says nothing about permissions, whether the note can later be edited or deleted, or what the response payload contains.

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 short sentences, front-loaded with the action, then visibility scope, then retry mechanics. Every clause carries information; nothing is redundant filler.

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 create-style mutation with full annotation coverage and no output schema, the description supplies enough to call it correctly: visibility, idempotent retry behavior, and pinned/category semantics. The remaining gap is the shape of the returned note, which no output schema documents either.

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 low (20%), with only idempotency_key documented in the schema, so the description must carry weight. It adds real meaning for 'pinned' ('keeps it surfaced') and enumerates the category values, but that enumeration merely repeats the schema enum without explaining what each category means, and it says nothing about client_id or content constraints.

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 concrete verb and resource ('Adds an office note to a client's record') plus the scope of the note (internal office note). It is trivially distinguishable from siblings like delete_client_note and pin_client_note, which imply removal or modification of an existing note rather than creation.

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 line 'Only the team sees it; nothing is sent' effectively excludes the messaging siblings (send_text, send_email) and tells the agent this is an internal record only. It also gives retry guidance for idempotency_key. It stops short of naming an explicit alternative or listing prerequisites, so it is not a full when/when-not statement.

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