update_note

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is known from structured data. The description adds genuinely useful patch semantics ('Other fields are kept as they are'), but does not warn what is destroyed (overwritten status values, removed tags that cannot be recovered) or that append is non-idempotent and will duplicate content on retry.

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?

Two sentences, no filler, with the core operation front-loaded and the preservation constraint immediately after the enumeration. Every clause carries information the agent needs and nothing is repeated from the schema or annotations.

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 no output schema required and a single required parameter, the description covers the essential contract: what can change, what is preserved, and the exact status vocabularies. Gaps remain around error behavior (unknown path), duplicate-tag handling, and non-idempotent append, which matter for a tool flagged destructive and non-idempotent.

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 only 40% and there are no enums, so the description carries real weight: it spells out the full allowed status vocabularies per note type (task/idea/decision states), which appears nowhere in the schema. The remaining gap is add_tags/remove_tags semantics — the description does not say whether adding an existing tag is a no-op or an error, or whether tag matching is exact.

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 pairs a specific verb ('Change a note in place') with the resource and enumerates exactly the three mutation families supported: status transitions, tag add/remove, and Markdown append. It also disambiguates the semantics from a full rewrite by stating 'Other fields are kept as they are', which lets an agent distinguish it from read_note/search siblings 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?

Usage is implied by 'in place' and the field-preservation clause, which tells the agent to prefer this tool for partial edits rather than a rewrite. However, there is no explicit when-not guidance, no mention of what to do when the note does not exist (e.g., use capture instead), and no statement that this is the only write path versus the queue_* or log siblings.

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