preflight

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description adds genuinely new behavioral context: results come back as cards where live clauses are binding and stale clauses point to their replacement decision, which shapes how the agent must interpret the payload. It stops short of noting pagination or how the token budget affects completeness.

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?

Two compact sentences with the core question front-loaded and the return-card explanation as follow-up support. Nothing is redundant, though the coined term 'good-law-aware' costs the reader a beat without being defined.

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?

An output schema exists, so the description needn't describe return values, and the annotations cover safety. What remains missing is proportionate to a four-parameter tool at 0% schema coverage: no explanation of `limit` or `budget_tokens`, and no clarity on what `paths` accepts, which would directly affect invocation.

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 0%, so the description must carry the load. It illuminates `task` and `paths` only at a conceptual level, without saying what a 'path' is (file path, graph node, workspace) or how the two inputs combine. `limit` and `budget_tokens` are never mentioned, leaving two of four parameters with no meaning anywhere.

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 description frames a specific retrieval task: finding decisions that constrain a given `task` or `paths` before acting. Phrasing it as a question ('Which decisions must you respect...?') is unconventional but concrete, and 'good-law-aware cards' plus the live/stale clause explanation tells the agent what kind of artifact comes back. It does not name or contrast any sibling such as search_decisions, so differentiation is left implicit.

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?

Timing guidance is implied by 'before doing `task` / touching `paths`', which tells the agent this is a pre-action check. There is no explicit statement of when not to use it, and no alternative tool is named for related lookups, so selection between it and siblings like search_decisions or decision_status is left to inference.

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