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

Annotations only declare readOnlyHint=true; the description adds real behavioral context beyond that: deterministic sort order, team-wide sharing semantics, and the follow-up-suggestion exclusion, plus a note that the embedded deal object is partially populated (open_task_count/next_task blank, go to query_deals). It stops short of describing rate limits or result-size behavior, but the safety profile is already covered by annotations.

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?

Uses summary/returns sections with the purpose and ordering stated first, then the use cases. Tight overall, though the returns field list is a long enumeration whose individual entries largely duplicate what the agent would learn from a response; it earns its place but is on the verbose side.

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?

With 10 params, no output schema, and no required params, the description compensates well: it documents ordering, sharing semantics, the exclusion rule, the paging shape (total/has_more/tasks), and clarifies which nested fields are unpopulated. Nothing an agent needs to call or interpret this correctly is missing.

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% and the schema itself already maps intents to params (due_before: 'For "overdue" pass today'; assignee_email: 'For "my tasks"'). The description restates some of that intent mapping in prose but adds no syntax, format, or interaction detail 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?

Opens with a specific verb+resource ('List CRM tasks') and immediately adds distinguishing scope: the Tasks view, sort order (earliest due first, undated last), and that tasks are team-shared. An agent can tell this apart from create_crm_task/update_crm_task and from query_deals without opening any schema.

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?

Names concrete user intents ('what's on my plate', 'what's overdue', 'what's next with Acme') and an explicit downstream workflow ('find a task's id before update_crm_task'). It also carves out an exclusion — Sliq-proposed but unaccepted follow-ups are not returned — which is exactly the kind of boundary an agent needs to avoid wrong answers.

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