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

With zero annotations the description carries the full burden and does so thoroughly: output is unsigned, no signature accepted, attorney-identity fields excluded, owner-restricted access, no database reads, no fee math, a $5 flooring rule, and an explicit warning that the result is a DRAFT to be verified. These are exactly the behavioral facts an agent cannot get from structured fields.

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?

Front-loads what the tool produces, then layers constraints and the fee-input rule in an ordered, readable sequence with no filler. It is dense but slightly long, and one sentence chains several negative constraints that could be more sharply separated.

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 16-parameter form-fill with no annotations and no output schema, the description adequately covers the major behavioral risks (unsigned, draft status, owner restriction, no computation). However, it leaves the majority of the input surface undocumented, so an agent could still mis-supply fields like feeReasons, currentRole, or the yes/no/na enums.

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% and 14 of the 16 parameters (wcbNumber, claimantName, dateRetained, feeReasons, currentRole, otherFees, servedNotice, deathBenefits, priorRetained, otherReasonText, otherReasonChecked, feeEquation, dateSubmitted, include_pdf) are explained nowhere. Only feeRequestedDollar and feeRequested are clarified, though the mutual-alternative relationship and the flooring rule are genuinely valuable. The description does not compensate for the coverage gap on the remaining parameters.

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 (fill), a named resource (OC-400.1 Application for Fee by Claimant's Attorney), and the exact output form (UNSIGNED PDF). It also distinguishes itself from the calculate_* siblings by declaring it reads nothing from the database and does no fee math, so an agent can tell it apart without opening any schema.

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?

Gives clear usage context: pass already-computed award numbers and supply either feeRequestedDollar or feeRequested. It explicitly states what will not work (signatures, attorney identity fields are filled elsewhere), which is strong exclusion guidance. It stops short of naming which calculation sibling to run first, leaving the upstream workflow implied.

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