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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description adds real behavioral context beyond that: the iterative re-scoring semantics of Sapiens passes and the binding-loss tradeoff when CDRs are humanized. It does not say what comes back, but an output schema exists to carry that.

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?

A single front-loaded sentence that opens with the action and then explains the algorithm after the colon; there is no filler. It is dense enough that splitting the algorithm summary from the option notes would improve scanability.

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 an 8-parameter tool with one required input, nested record shapes and an output schema, the description gives enough of the algorithmic contract to call it correctly. Remaining gaps (return payload, numbering prerequisites) are covered by the schema and output schema, so nothing critical is absent.

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 the baseline is 3. The prose restates what the schema already says for the key knobs (parental CDRs retained, optional Kabat Vernier zone, iterations as Sapiens passes), adding little semantic detail the schema does not already provide.

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 and resource (humanize an antibody variable domain) and goes further by naming the engine (Sapiens / BioPhi) and the mechanism (score positions against human repertoires, take the top framework residue, keep parental CDRs). What is missing is any naming of the close sibling graft_antibody_cdrs, which sounds like it does overlapping work, so an agent cannot fully discriminate on the description alone.

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?

Usage is implied rather than stated: the tool is for humanizing while preserving binding, and the humanizeCdrs note warns that extending humanization into the CDRs raises the risk of losing binding. There is no explicit 'use this instead of X when Y' routing against graft_antibody_cdrs, compare_antibodies or optimize_sequence, leaving the agent to infer the choice.

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