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

Annotations already cover the read-only/idempotent safety profile, so the description correctly spends its budget elsewhere: it discloses visibility scoping ('you may see', 'if you can see it' for accountId), the company timezone used by dueWindow, and that the response returns a true total plus pages. These are behavioral facts not obvious from 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?

Front-loads the verb and resource, then packs filters, return behavior, and the exclusion into three tight sentences with no filler. Slightly dense but every clause carries information.

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?

A 9-parameter read tool with a full output schema; the description covers scope, all filter families, timezone semantics, pagination behavior, and the one hard exclusion. Nothing an agent needs to invoke it 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%, so the schema already documents all nine parameters including the enum meanings and datetime bounds. The description largely restates those filters and adds only the timezone framing, which is a baseline-3 contribution.

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 ('List CRM follow-up tasks') and scopes them as 'portal tasks, owned by users' with visibility limits ('you may see'). It distinguishes itself from the broader list_tasks by noting 'Unassigned tasks cannot be filtered here', though it never names that sibling explicitly.

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?

Enumerates the filter dimensions an agent can use (status, owner, account, dueWindow, dueAfter/dueBefore) and gives an exclusion ('Unassigned tasks cannot be filtered here'). The exclusion implies where those tasks live but does not name the alternative tool, so routing guidance is clear but not complete.

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