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

Annotations already declare write/idempotent/destructive/open-world, so the safety profile is covered. The description adds a trait annotations cannot express: partial-update semantics ('only the fields you pass change'), which is critical for an agent deciding what to send. It does not warn that list-valued fields like tag_ids replace the whole list, but the schema field descriptions cover that.

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 compact clauses and an endpoint, all front-loaded: write marker first, partial-update rule second, conversion hint third. No sentence is redundant given how much is packed into so few words.

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 16-parameter mutation with full schema coverage and no output schema, the description supplies the essentials: mutation type, partial-update behavior, conversion path, and endpoint. No return-value explanation is needed since no output schema exists; only a list-replacement caveat would strengthen it, and the schema already flags tag_ids as a 'full list'.

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 description coverage is 100% across 16 parameters, so the schema carries the burden; baseline is 3. The description only elaborates on the 'type' parameter (lead-to-contact conversion), which the schema already frames as 'Convert the record to a Lead or a Contact', so the added meaning is marginal.

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 ('change fields of a person') plus the update semantics ('only the fields you pass change') and the underlying operation (PUT /people/{id}). It is clearly distinguishable from create_person and the other update_* siblings by resource. The only shortfall is that it never explicitly contrasts itself with a sibling, which the name already largely handles.

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?

It gives one genuine usage rule ('Pass type Contact to convert a lead') and implies partial-update usage, but offers no when-to-use vs. when-not guidance and no pointer to alternatives such as create_person for new records. Usage is inferable rather than stated.

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