candidates

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

With no annotations provided, the description fully carries the burden of behavioral disclosure, and it does so thoroughly. It explains that leads are never suppressed due to constant size, nearby guards, or absent input flow; describes the paged result structure; notes serialization per session and the expensive first cold bind; and explains how temporal evaluation degrades on hard_stop expiry. This is a comprehensive behavioral disclosure.

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 four sentences with no filler. The main purpose is front-loaded, followed by critical behavioral caveats and alternative tool routing. Each sentence earns its place and the structure flows logically from core function to edge behaviors.

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 10 parameters, no annotations, and no output schema, the description covers the most important behaviors and key parameters, but leaves several parameters (limit, offset, cursor, domain, constructor_id, language) without explanation. It also lacks a description of the exact lead structure beyond paging fields. While the core is well-covered, the incomplete parameter documentation prevents a higher score.

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 only 40%, so the description must compensate. It adds meaningful context for temporal and hard_stop (e.g., the temporal_evaluated flag), and explains the pagination fields (leads, total, next_offset). However, it does not describe limit, offset, cursor, domain, constructor_id, language, or format beyond what the schema already says, leaving these parameters without additional semantic guidance.

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 uses direct verbs ('Enumerate and rank') and a precise resource ('every observable obligation site as leads'), and immediately distinguishes itself from the sibling candidate_census by noting it provides a pointer rather than a full roster. This leaves no ambiguity about what the tool does and how it differs from similar tools.

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 gives explicit guidance to call candidate_census for the full coverage roster, and instructs when to set temporal=false for the fast path ('use it when a large graph makes the full bind run long'). It also states this is 'not a safety check', implying it should not be used for safety verification. This is strong, though it doesn't enumerate all alternative siblings or exhaustively list when not to use the tool.

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