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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description adds real context beyond that: highlights can only be modified, not created, and passing null clears the note, which is a data-loss behavior the annotations alone do not convey. It falls short only on edge cases like an invalid or foreign highlightId and whether the caller must own the highlight.

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 mutation, then the null-clear rule, then the sibling routing. No filler or repetition of the 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?

For a three-parameter mutation with no output schema and clear annotations, the description covers what changes, how to clear, where the ID comes from, and where not to use it. Remaining gaps are error behavior and return value, though annotations and the idempotent/last-write-wins semantics cover much of the risk profile.

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 0%, so the description must carry the load, and it does for the two ambiguous parameters: note is the reader's note and accepts null to clear, and highlightId is sourced from list_notes. The color parameter is only gestured at with 'its color', leaving the allowed enum values to the schema, and the 2000-character note limit is also schema-only.

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 specific verb (changes) and specific fields (note, color) on a specific resource (highlight from the in-app reader). It also disambiguates from siblings: highlightIds come from list_notes, new highlights are created in the reader, and add_note is the tool for quotes.

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?

It gives explicit routing: use list_notes to obtain highlightId, note: null to clear, and add_note when the goal is saving a quote rather than editing an existing highlight. This is when-to-use, when-not-to-use, and the alternative in one short block.

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