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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description is not responsible for the safety profile. It does add real context beyond that: newest-first ordering, "safe summaries only" (implying redaction), and scoping to "granted projects". However, with 17 parameters it never explains which filters apply in calendar mode versus activity mode, which is the main behavioral ambiguity an agent faces.

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?

Short, front-loaded, and free of boilerplate; the mode split and paging note arrive in the first two sentences. The telegraphic fragments ("calendar: true: the calendar") are efficient but slightly cryptic, and "Page with limit/offset or cursor" is left ambiguous about whether they combine.

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 17-parameter, zero-required tool with a nested object and no output schema, the description is far too thin. An agent cannot infer which filters are meaningful per mode, what units since/due_after accept, or what include_removed changes. The mode distinction is covered; the filtering surface is not.

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 only 6%, so the description bears most of the burden and covers only calendar, limit, offset and cursor. The other thirteen parameters (q, kind, query, since, source, status, agent_id, priority, due_after, due_before, project_id, review_status, include_removed) receive no explanation, including the nested free-form query object. "Page with limit/offset or cursor" is a useful hint that the two paging styles are exclusive, but that is the only genuine addition.

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?

Names a specific verb and two concrete resources: "Read what changed, or what is scheduled", then pins the modes to the activity log default and the calendar when calendar=true. An agent can tell what the tool returns without opening the schema, though it never contrasts itself with siblings like list_tasks or search.

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 default behavior is stated clearly ("Default: the activity log") and the condition that switches modes is given ("calendar: true: the calendar for granted projects"). There is no when-not-to-use guidance and no pointer to an alternative tool for related reads, so usage is implied rather than fully guided.

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