board_update

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the status vocabulary, the evidence prerequisites for terminal states, and two important guard rails around asks (non-editable, cannot complete with open children). It omits auth requirements (an api_key parameter exists) and what happens on an invalid transition, but the disclosed rules are substantive and non-obvious.

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?

Three dense sentences, front-loaded with the action and status enum before the conditional rules. No filler. The phrase 'a new measured `current` for a target' is slightly cryptic, but overall the structure is efficient.

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 an 8-parameter mutation tool with no annotations, no output schema, and 0% schema coverage, the description covers the highest-value semantics (status, evidence, ask constraints) but leaves several parameters and any permission/return behavior unaddressed. Adequate to call it correctly in common cases, incomplete at the margins.

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 0%, so the description must compensate. It successfully explains status (with the enum values the schema lacks), current (a new measured value for a target), and evidence (with per-status content requirements). However, goal, path, agent, api_key, and id remain completely unexplained in both schema and description, leaving half the parameters opaque.

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 ('Move a board item') and then enumerates the valid status values (open|doing|blocked|done|dropped), so an agent immediately knows this mutates a board item's state. It does not explicitly name the sibling to use instead (board_add) for creation, so it falls just short of full sibling differentiation.

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?

Provides concrete conditional rules: done requires evidence (commit, file, benchmark, item id, URL), dropped requires a reason in evidence, asks cannot be edited, and an ask cannot be done while child items are open. These are real when/when-not constraints, though no alternatives (e.g. board_add for new items) are named.

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