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

Beyond the readOnly and non-destructive annotations, the description discloses the exact return fields, the exclusion of integration-managed feeds, the error sentinel project_id_required, and the non-paginated complete-return behavior. This gives the agent a full behavioral model of the operation beyond what annotations alone provide.

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?

Every sentence adds a distinct fact: the sibling distinction, item shape, parameter semantics, error recovery, feedId usage, standalone-only exclusion, and pagination behavior. Despite being longer than typical descriptions, there is no filler and the most important scoping detail is front-loaded.

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 one-optional-parameter read-only list tool, the description covers the return schema, error handling, exclusions, and pagination, so an agent can select and call it correctly without needing additional lookups. There is no output schema, but the inline item field list fully compensates.

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?

The input schema provides only 'optional integer project_id' with zero description coverage, so the description carries the full burden and succeeds. It explains the semantic difference between passing and omitting project_id, the error condition that triggers its use, and the fact that each result carries its projectId even in the cross-project case.

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?

The description states a precise verb and resource: it lists the customer's already-created feeds, explicitly distinguishing these from the catalog of feed types by naming list_feed_templates as the alternative. It even enumerates the returned item shape, removing ambiguity about what a 'feed' is in this context.

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 explicitly says to use list_feed_templates for the catalog, and explains the optional project_id behavior with clear conditions: with it you get that project's feeds, without it you get all projects' feeds. It also handles the project_id_required error by directing the agent to list_projects to pick a project, and maps feedId to feed_id for get_feed/verify_feed_attributes.

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