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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description is free to add operational context. It does: list results come in queue order, filtering works via flat arguments or a query object, and paging works through limit/offset or cursor. It also notes that a single-task read includes summary and notes, which is behavior no annotation conveys.

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 dense and front-loaded: the domain exclusion comes first, then the two modes in order. Every sentence carries information, though the single run-on paragraph with parenthetical status definitions makes the paging and filtering details slightly hard to scan.

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 17 optional parameters, no output schema, and a nested query object, this definition is thinner than the tool's complexity warrants. It covers mode selection, ordering, and paging adequately, and it sketches the single-task return, but the bulk of the filter surface is undocumented, so an agent would have to guess at most arguments.

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% across 17 parameters, so the description must carry the load, and it does not. It gives meaning to task_id, status, limit/offset, cursor and query, but leaves q, kind, since, source, agent_id, priority, due_after, due_before, project_id, review_status and include_removed entirely unexplained in both schema and prose. An agent cannot tell how those filters combine or what units since and the due_* bounds expect.

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 opening line gives a specific verb and resource ("Read tasks") and immediately rules out a sibling domain ("not projects"), so an agent can separate it from get_project without opening a schema. It then splits the tool's two modes explicitly: no task_id means a list, task_id means a single task. That is a complete purpose statement in two clauses.

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 clearly states the condition selecting each mode ("With no task_id" vs "With task_id") and explains that status "open" returns every pending task while "done" returns finished work, which is real routing guidance. It stops short of naming a write alternative such as save_tasks or a search alternative, so the when-not-to-use side is only implied by "Read tasks, not projects."

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