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 so well: it discloses the returned content (choices with basis, Jev's pick, distribution, confidence, bar clearance at 0.8 default), the cost behavior of dry:true ('without spending a call'), and batch's ready_jobs calibration criteria (Wilson interval, n ≥ 5, width ≤ 0.35). It stops short of stating whether the call mutates state or what auth/rate-limit constraints apply.

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 and the text is compact, but the high jargon density and colon-heavy run-on sentences make it hard to parse, so not every clause cleanly earns its place for a first-time reader. It is dense rather than wasteful.

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 a 10-parameter tool with no output schema, no annotations, and 10% schema coverage, the description is thin on how the phases relate and what the majority of inputs (task, seller, skills, api_key, chain_id) accomplish. It covers return content and cost but leaves too many required pieces to inference.

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 only 10% (just price), so the description must compensate and partially does: it explains phase values, bar (0.8 default), dry behavior, and typesafe_key. Six of ten parameters (task, price, seller, skills, api_key, chain_id) remain undocumented in both schema and description, leaving a real gap.

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 states the mechanism (presenting every field of a coordination phase as a typed multiple-choice question over live data, answered in one battery) and lists the phases matching the enum. However, private jargon ('Jev pad', 'calibrated battery', 'Jev fills in the numbers') obscures what the tool concretely does, and it does not distinguish itself from siblings like taifoon_hire_suggest or taifoon_hire_assemble.

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?

There is one implicitly useful usage hint ('dry:true returns the choices without spending a call'), but no explicit when-to-use guidance or comparison against the many hire_* siblings. An agent cannot tell from the text when to reach for this pad instead of taifoon_hire_suggest, taifoon_hire_path, or taifoon_hire_assemble.

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