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

Annotations flag destructiveHint=true and idempotentHint=true, and the description adds the crucial operational context for that destructiveness: the new text 'replaces the old text', so the caller must pass the full merged text to avoid data loss. This meaningfully extends the raw annotation, though it doesn't address auth or rate limits.

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?

Front-loads the purpose and content enumeration, then closes with the merge and authoring instructions. The opening sentence is dense but every clause carries routing or behavioral payload; no filler sentences.

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 single-parameter write whose return value is covered by an output schema, the description supplies purpose, triggering context, the destructive-replace warning, the read-merge prerequisite, and authoring constraints. Nothing an agent needs to call it safely is missing.

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 100%, so baseline is 3, but the description goes further by specifying what the string should contain (standing application facts), how to author it ('in the user's words; never invent facts'), and that it is a full replacement rather than a patch — genuine meaning beyond the schema's terse field description.

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+resource ('Save standing facts about the user') and names the exact target field ('More about you' text in Settings), enumerating concrete content types like work authorization, notice period, and desired salary. This lets an agent distinguish it from the sibling update_my_profile without opening a 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?

Explains when the facts are consumed ('on every future application' via Apply with AI) and mandates a pre-step: read get_my_profile first and merge so nothing is lost. It names the alternative read tool and the workflow condition, leaving little to inference.

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