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

Annotations only say this is a non-read-only, non-destructive write; the description adds the traits that actually matter in operation: the call rewrites the bio via web research, may take several minutes, must not be retried, and reports outcome through web_enhanced_bio with a documented fallback when no web data exists. Minor tension with openWorldHint=false, since the backend consults the web, but that does not contradict the core write semantics.

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 purpose, then the latency/no-retry warning, then how to verify the outcome. Every sentence carries distinct, actionable information with no filler.

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 tool whose schema is a large nested object with zero field descriptions and no output schema, the description covers only the asynchronous rewrite behavior. An agent still cannot tell which of the ~40 fields are required or meaningful, what 'database' refers to, or what the return payload looks like beyond a single mentioned field.

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?

There is effectively one body parameter containing ~40 nested fields at 0% schema description coverage, and the description explains none of them. It only hints that a bio is passed in and may be replaced ('the bio stays as passed'), leaving the required name/blurb/database and the many bio_grade/key_points variants entirely undocumented.

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 ('Create a profile for your team'), which cleanly separates it from the create_* siblings that target campaigns, templates, and labels. It does not explicitly contrast with any single sibling, but the resource noun makes selection 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?

The description gives a clear 'when not to' signal — do not retry while the rewrite is running — and implies you call it to add a teammate profile. However, it never states prerequisites (e.g., which database to target, whether the profile must be unique) or points to list_profiles/archive_profile for adjacent workflows, so routing guidance is only implied.

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