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

The description goes well beyond the readOnlyHint annotation: it discloses that tasks are shared across the user's team, that follow-up suggestions not yet added are excluded, and that the results are sorted. The returns block further reveals that open_task_count and next_task on linked deals are not filled here, which is precise behavioral transparency.

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?

The description is front-loaded with the core behavior and use cases, and the returns block is structured and concise. Every sentence adds value, from the sort order to the exclusion of follow-up suggestions. It is detailed but not bloated, earning a 4.

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 9 optional parameters and no output schema, the description compensates by providing a full returns shape and clarifying data semantics (e.g., linked deal fields may be null). The annotations cover read-only safety, while the description covers behavior, sorting, filtering context, and the update workflow. Nothing essential 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?

All 9 parameters already have detailed descriptions in the input schema (coverage 100%), including examples like 'For 'my tasks' pass the user's own email' and 'For 'overdue' pass today.' The main description adds context like sorting and team sharing but doesn't add parameter-level meaning beyond what the schema provides. Baseline of 3 is appropriate.

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 specific verb ('List') and resource ('CRM tasks'), names the 'Tasks view', and specifies sorting behavior (earliest due first, undated last). It distinguishes from siblings like update_crm_task by explicitly mentioning finding a task's id before updating, and it gives concrete use cases like 'what's on my plate' and 'what's overdue'.

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?

The description explicitly says 'Use this for...' with several concrete scenarios and points to update_crm_task as the follow-up. It also notes a limitation (follow-up suggestions not included) that helps agents know when the tool won't apply. However, it doesn't name an alternative for the excluded case, so it stops short of full when-not guidance.

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