explain

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

With no annotations, the description carries full disclosure. It explicitly warns that 'provenance and guard are evidence, not verdicts' and that an empty cone means 'nothing observed under this tier,' not 'unreachable.' It also details the temporal fast path and hard_stop degradation behavior, including the result's 'temporal_evaluated' flag. This is substantial and non-obvious behavioral context.

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 a single dense paragraph with long, compound sentences full of technical jargon (e.g., 'bounded reverse value-flow cone,' 'census->candidates->detail->sources_of->read_body chain'). While every sentence adds information, the sheer length and convoluted phrasing reduce usability. It could be split into bullet points or shorter sentences without losing content.

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?

Given the tool's complexity (8 params, no output schema), the description covers the essential behaviors: what result is produced (obligation, guard, cone, source), interpretation of results (evidence vs verdicts), fast-path and timeout behavior, and invocation patterns. It mentions result flags (temporal_evaluated) which is helpful. No critical gaps apparent for an expert user, though it assumes domain familiarity.

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 100%, so baseline is 3. The description adds meaning by clarifying the mutual exclusivity of candidate_id vs file+line, and by explaining the temporal parameter's effect on evaluation completeness. However, it doesn't add details beyond what the schema already provides for parameters like format, max_source_chars, or provenance_limit. It's adequate but not enriching.

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 clearly states what the tool does: it produces a composite 'judgeable picture' from a candidate or sink location, bundling obligation, guard, reverse flow cone, and source code. It distinguishes itself implicitly by describing a chained pipeline (census->candidates->detail->sources_of->read_body) that no sibling explicitly offers, though it doesn't name a specific alternative. The verb 'explain' is vague, but the resource and outcome are concrete.

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 instructs to 'Pass candidate_id, or file and line,' giving the primary invocation choices. It also mentions the temporal parameter for a fast path but doesn't explicitly say when to choose this tool over other siblings like candidate_detail or sources_of, nor does it state exclusions or prerequisites. Some context is given (e.g., use temporal=false for large graphs), but no comparative guidance.

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