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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds real context beyond that: the assignee defaults to the authenticated caller, limit defaults to 25, and it names the returned fields (assigneeName, reporterName, sheetName plus *Id FKs) and which to prefer in prose. It does not discuss pagination beyond limit, so it stops short of a 5.

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?

It is front-loaded with the purpose and then walks through filters in a logical order, with no wasted sentences. There is mild redundancy, since the state/overdue semantics are also spelled out in the schema, but each sentence still carries invocation guidance.

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 a full output schema and strong annotations, the description covers everything needed to call it correctly: defaults, filter interactions, the overdue override, and return-field guidance. Nothing an agent needs 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 coverage is 86%, so the baseline is 3 and the schema already documents state, overdue, sheetId, due window, limit and assigneeUserId. The description adds usage-oriented meaning the schema lacks, notably the 'omit for my tasks, never guess the id' framing for assigneeUserId and the prose-vs-FK preference for returned name fields, which lifts it above baseline.

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 opens with a specific verb+resource ('List tasks') and immediately scopes it with the filters it supports. It is clearly distinct from write-oriented siblings like task.create and from other resource reads (calendar.read, sheet.read). An agent can tell what this tool does without opening the 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?

It gives explicit when-to-use rules keyed to natural user phrasing: 'my tasks' / 'what's due' means omit assigneeUserId; only set it for a specific other person whose numeric userId you already hold. It also names the correct filters (state, overdue) for common intents and warns 'Never guess this', leaving nothing to inference.

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