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

Annotations already declare readOnlyHint/openWorldHint=false/destructiveHint=false, and the description's "Read-only" merely restates that. It does add genuine behavior: newest-first ordering, that 'blocked' is the TZ-012 clarification state returned with questions, and which provenance fields each row carries (author_user_id/origin/trust, is_agent_directive).

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 purpose and scope in one sentence, then filters, then output shape. The trailing "Compact: 'fields', 'cursor' (next_cursor), mode='summary'..." is telegraphic and slightly choppy, but no sentence is wasted.

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 no output schema, the description usefully lists what each returned task contains and explains pagination via next_cursor and the summary mode's return size. For a 7-parameter read tool this is nearly sufficient; only 'limit' semantics and any result-size caveats are 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 only 43%, so the description must compensate and largely does: it defines 'blocked' semantics, what author_trust selects (trusted vs external DATA), that origin is the inbound channel, plus fields/cursor/mode behavior. Only 'limit' is left undefined, which is a minor gap given its 1-100 bounds.

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 with scope: "List the caller's personal tasks from their active workspace, newest first." That clearly separates it from write-oriented siblings like create_tasks or convert_meeting_actions_to_tasks, though no sibling is named explicitly to route the agent.

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?

Explains that all filters are optional and gives a concrete rule for mode='summary' (counts + top rows, a few KB), which tells the agent when to prefer it. It offers no exclusions or named alternatives for cases like searching other users' tasks, so 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.