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

Annotations already declare mutation (readOnlyHint=false), destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: it is a partial patch ('send only the fields to change') and passing url: null removes the link, which explains the destructive facet concretely.

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-loading the mutation, then the id source, then the patch/null rules. No filler and every clause carries information an agent needs.

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 5-param, no-output-schema mutation tool, the description covers purpose, id acquisition, partial-update semantics and link removal. Minor gaps remain: site-key/account scoping requirements and what happens when the id is unknown, both of which affect correct invocation.

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%, so the description has to compensate; it maps three of five parameters (label, ts as 'time', url) and adds the null-semantics for url that the schema's anyOf does not explain. Only `site` is left to the schema's own description, and `annotation_id` is covered indirectly via 'get the id from list_annotations'.

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 ('Change') and resource ('a chart note/annotation') plus the three mutable fields (label, time, link), which cleanly separates it from add_annotation, delete_annotation and list_annotations by inference. It does not name those siblings explicitly, so an agent must reason from the verb rather than being told.

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 actionable workflow context: 'Get the id from list_annotations' routes the agent to the correct prerequisite tool, and 'Send only the fields to change' defines the partial-update contract. It does not state when not to use it (e.g. to create or remove a whole annotation instead).

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