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

Annotations already declare this as a non-read-only, non-destructive, non-idempotent, closed-world write, so the safety profile is covered. The description adds genuinely new behavioral content: an editorial policy (no links, names, or secrets) and the one-fact-per-note granularity rule. It does not disclose that repeat calls create duplicate notes (idempotentHint=false), whether notes are attributed or moderated, or whether a note can later be revised or removed.

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 the atomicity/length rule, then the content prohibitions. No redundant framing and no restatement of the title alone.

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 four-required-parameter write tool with full schema coverage and annotations covering safety, the description supplies the missing piece an agent actually needs: what content is acceptable. Remaining gaps are secondary, mainly the absence of return-value expectations and any warning that non-idempotent writes can duplicate.

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 100%, so the parameters, including the kind enum and the 40-500 character rule, are already documented. The description does add meaning for the text field by specifying what to state and what to exclude ('State what happens; do not tell the reader what to do with other systems'), but it says nothing about topic slug conventions or the session parameter, so it stays at baseline.

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 names a concrete verb and resource ('Add a note') and constrains it to first-hand observations in this context, which clearly separates it from the read-oriented siblings (lookup, topics, confirm). It stops short of naming any sibling explicitly, so the differentiation is inferential rather than stated.

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 implied through the content rule 'from something you observed yourself in this context' and 'one fact per note', which tells the agent what qualifies. There is no explicit when-to-use, when-not-to-use, or routing to alternatives such as lookup or confirm, nor any mention that a session must be established first (that only appears in the schema).

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