Ask the project brain a question (whole-brain, correction-aware answer)

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

With no annotations, the description carries the full burden and does so well: it discloses the semantic-ranking path and its on-device-model dependency, the keyword-only fallback, in-progress brain behavior, inclusion of superseded/archived history with flags, and correction attachment for stale cards. It also clarifies it returns a synthesis context rather than prose — a genuinely non-obvious behavioral trait.

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 purpose is front-loaded, but the body is a single dense wall of text mixing install instructions, fallback behavior, correction logic, and benchmark statistics ("60 of 102 test questions instead of 55"). Much of it earns its place, yet the measurement asides and install command add length without materially helping tool selection.

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?

There is no output schema, yet the description describes the return shape (full cards + provenance + lifecycle) and its intended downstream use. Combined with the fallback, lifecycle, and temporal behavior disclosures, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3, but the description adds real value: it explains as_of semantics beyond the schema's wording and prescribes the "Also: <8–14 words>" suffix on the question to widen recall, which is not derivable from the schema. The k cap and canvas default are already in the schema, so it stops short of 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 specific verb+resource ("Answer a natural-language question from the WHOLE project brain") with concrete example questions, and explicitly distinguishes itself from the sibling search_canvases. An agent can tell what it does and how it differs from keyword lookup 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?

Gives an explicit routing rule: "Prefer this over search_canvases when the user asks a QUESTION (not a keyword lookup)." It also names the as_of condition for answering historical questions, so both when-to-use and which-alternative scenarios are covered.

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