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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered by structured data. The description adds the navigational context of the REST endpoint and the set of fields exposed, but says nothing about pagination behavior, default result count, or ordering — gaps the agent must infer.

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 terse fragments, front-loaded with the core action and field inventory. The trailing "GET /tasks/." is somewhat extraneous for an agent that cannot issue raw HTTP, but it is short enough not to bloat the definition.

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 zero-required-parameter read tool with 100% schema coverage, full annotations and no output schema, the description supplies what is missing: what the tool returns and which fields are searchable. Only the absence of any sibling routing (get_task vs list_cases vs list_deals) keeps it from being fully 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 description coverage is 100%, with sort, limit, start and filters all fully documented inline (including the next_start paging pattern and AND semantics for filters). The description only hints that filtering is possible via "Filter e.g. on due_date", adding essentially nothing beyond the schema, so baseline 3 applies.

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?

Clear verb+resource ("list or search tasks") plus an enumeration of the searchable/returnable fields (title, due date, completion date, assigned users, linked deal/contact/case) and the backing endpoint. It distinguishes itself from cogmento_get_task and cogmento_create_task by implication, but never names a sibling to contrast with.

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?

"Filter e.g. on due_date" gives a single concrete example of narrowing results, and the verb "search" implies retrieval rather than mutation. There is no explicit statement of when to use this versus cogmento_get_task for a single record, or versus cogmento_list_cases/list_deals for other entity types — usage is only implied.

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