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

Annotations already declare readOnly=false, idempotent=true, destructive=false; the description adds the non-obvious merge semantics — unspecified fields are preserved — plus a worked example, which is genuine context beyond the annotations. It stops short of saying how nested objects are merged (deep merge vs. replace) or what the response contains, which matters for a mutation with nested-object input.

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?

Two short sentences, front-loaded with the merge semantics, then the example, then the routing hint. Nothing is redundant with the title or schema and nothing could be trimmed without losing meaning.

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 four-parameter mutation with no output schema, the description covers the core merge behavior but omits merge depth for nested objects, whether fields can be nulled/removed, and what the call returns or errors on. Adequate to invoke, not quite complete.

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% and the schema already documents data ('Only the fields to change'), api_key, and collection; the description's merge explanation reinforces data but adds little new syntax or format detail. record_id remains undocumented in both, and no guidance is given on how keys in data map to stored fields.

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 operation on a specific resource: merge given fields into a record while keeping the rest, with a concrete example. It implicitly contrasts with the sibling update_record via 'Use this for most edits,' but never names that sibling, so the differentiation is inferential rather than explicit.

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?

'Use this for most edits' signals this is the default edit path and hints at a heavier alternative, but it never names update_record, never states when partial-merge is wrong (e.g., replacing a list or clearing a field), and gives no prerequisites.

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