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

Annotations already flag readOnlyHint=false and idempotentHint=false, but the description reinforces the non-idempotent behavior with 'Creates a new note each call', which is a meaningful warning that duplicate calls produce duplicate notes. It also exposes the underlying POST endpoint, giving the agent grounding in the actual operation.

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, front-loaded clauses with zero filler. The operation type and the key behavioral caveat both appear before the endpoint detail.

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 tool with no output schema, the agent is left guessing whether the new note's id is returned and whether it can be used for follow-up operations. The core action and its non-idempotency are covered, but the result contract is not.

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 75%, so title, body, and important are already documented in the schema. The description adds only that the supporter is the target record, without explaining the role of supporter_id (the one undocumented parameter) or what 'important' changes downstream. Baseline 3 is appropriate.

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 and resource ('add a note to a supporter's record'), which cleanly separates it from the sibling funraise_create_household_note. It doesn't name that sibling explicitly, but the scoping to a supporter is unambiguous.

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?

'WRITE:' and 'Creates a new note each call' imply this is for adding new notes rather than updating existing ones, but it never says when to use this versus funraise_create_interaction or how to check for an existing note first. Usage is implied rather than stated.

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