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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real context beyond that: visibility scoping, the 50-item cap, cursor pagination, the return shape, and a prompt-injection warning about untrusted CRM field values, which is genuinely useful for an agent handling returned data.

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-loaded with purpose, then capabilities, then the return shape, with the security warning isolated as its own short paragraph. Dense but every clause maps to a real parameter or behavior; only the capability list is slightly packed for one sentence.

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 an 8-parameter, nested-filter, no-output-schema list tool, the description supplies the missing return contract ({items, nextCursor, totalCount}), pagination model, and column guidance via describe_object. It is nearly complete; a brief note on obtaining the next cursor or the workspaceId conditional would close the remaining gap.

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 only 13%, so the description carries most of the burden and largely does: it names search, fieldKey/operator-driven filters tied to describe_object, sortBy/sortDirection, cursor pagination, and the limit ceiling. It stops short of explaining cursor mechanics (pass nextCursor back), filter combinator nesting, or the conditional workspaceId requirement, which the schema partly covers.

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 ('Lists records of one object type') plus a scope qualifier ('with exactly your visibility'), which separates it from get_record and cross-object search at a glance. It is clear but does not explicitly name a sibling to avoid, so it falls just short of the top band.

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?

Usage is implied: the mention of 'fieldKey/operator from describe_object' routes the agent to describe_object for filter metadata, and the limit/pagination notes signal a paged listing. However, there is no explicit when-to-use versus search, get_record, or list_deleted_records, and no conditions for choosing among them.

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