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

Beyond the annotations it discloses genuinely load-bearing behavior: all-or-nothing atomicity, duplicate merging, title-based skipping of items already in a list, a 20,000-character cap, and the metadata comment grammar including 'needs' dependency references. The dedup/skip rule is consistent with idempotentHint=true rather than contradicting it.

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?

Purpose is front-loaded, but the body is a single run-on block of semicolon-chained clauses, including awkward phrasing like 'What only the human can do is a request and a decision of theirs a question, not also a task.' The format spec and metadata grammar would be far more usable as structured bullets; no sentence is superfluous, but the packaging costs readability.

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?

Covers format, limits, dedup, atomicity, dependency references and project scope for a schema-complex, nested-parameter mutation tool with no output schema. The one gap is what happens on success or rejection beyond 'all in or nothing' — no mention of counts, error reporting, or what the caller gets back.

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 already 100%, so the baseline is 3; the description goes further by spelling out the Markdown grammar (## headings, checkbox syntax, indented notes, subtasks, question options with '(recommended)') and a full metadata comment field list (id, by, at, needs, prio, done, done-by, answer, answered-by) that the schema does not document. It is dense and partly overlaps the schema's own 'items as Markdown' phrasing, which keeps it off a 5.

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 concrete verb and destination: bring work kept elsewhere (TODO files, issues, other tools' lists) into the lists, in one call. 'In one call' implicitly distinguishes it from the single-item sibling 'add', but no sibling is named outright, so the agent must infer the boundary.

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?

Gives a hard precondition ('once the human says yes') and a scoping exclusion ('a log of past work stays in its file: bring only the open work it names'), plus 'this project only'. It never routes the agent to 'add' or another alternative for single items, so the when-not guidance is partial rather than explicit.

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