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

Beyond annotations (readOnly=false, idempotent=true, destructive=false), the description adds that the operation is a targeted update ('and/or'), that the note is free text with examples, and that the tool 'reads back the updated row' — clarifying the return behavior despite the lack of an output schema. It also states the prerequisite that the creator must already be saved, which helps avoid misuse. No contradiction with annotations.

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: the first states action and scope, the second defines the two fields with their value domains, and the third covers return behavior, key lookup, and cost. Every sentence adds value, and the most critical scoping ('already saved') is front-loaded.

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 simple 3-parameter update with idempotentHint and destructiveHint already set, the description covers the workflow prerequisite, the accepted statuses, how to resolve the key, and the return behavior. It does not explicitly note that status and note are both optional in the schema (only key required), but 'and/or' implies at least one should be provided, which is sufficient for an agent. No output schema exists, so mentioning 'reads back the updated row' is the right amount of return-value detail.

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 already documents key and note (67% coverage); the description reinforces status as 'outreach status' and lists its enum values, though this duplicates the enum. The note examples ('deal terms, rate, what was sent') add modest semantic color beyond the schema's clear/replace semantics, but the description does not substantially illuminate parameter formats or constraints not already in the schema.

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 the exact operation ('Set'), the target resource ('a creator already saved in the swipefile'), and the precise fields affected (outreach status, note). This clearly differentiates it from siblings like save_to_swipefile (creation) and delete_creator (removal) without ambiguity.

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?

The description embeds the workflow context ('find_creators → save_to_swipefile' or the heart icon), and instructs 'Use list_swipefile to find the key' — telling the agent how to obtain the required key and signalling this operates on existing swipefile rows. It does not explicitly name save_to_swipefile or delete_creator as alternatives for add/remove, so the exclusion 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.