predict_structure

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

With no annotations, the description carries the full burden and does a good job: it discloses asynchronous execution ('background job', 'may return a job_id to poll with get_job'), the computed confidence outputs, and the side effect of writing PDB files to disk with pLDDT in the B-factor column. It stops short of GPU contention/time expectations, but the operational profile is well covered.

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?

Three short sentences, each earning its place: capability first, return artifacts second, execution model third. Front-loaded with the core action and free of filler.

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?

Even though an output schema exists, the description usefully complements it with output artifacts and async semantics, and it covers the GPU/background-job behavior an agent needs to call correctly. Only minor gaps (expected runtime, GPU capacity limits, failure behavior) remain.

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%, with both 'sequence' (raw or FASTA, ≤20 records) and 'num_recycles' (more helps hard targets) documented in the schema itself. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 ('Predict 3D protein structure') plus the concrete method ('with ESMFold on a GPU'), which cleanly separates it from siblings like search_homologs, translate_sequence, or seq_stats. An agent can identify the tool without opening the 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?

The description implies usage ('predict 3D protein structure') and adds operational routing ('Runs as a background job; may return a job_id to poll with get_job'), but never states when to prefer this tool over alternatives such as search_homologs for structural inference by homology. Usage is implied rather than explicit.

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