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

Annotations already declare it is a non-read-only, non-destructive, closed-world operation, so the description's main job is to add mutation semantics. It implies the open record is modified ('put ... onto the open record') but never says whether existing features are replaced, appended to, or merged — the single most consequential behavior for a feature-annotation write. The note about GTF lacking sequence is useful domain context but not 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?

Two tight sentences, front-loaded with the action, with no filler or repetition. The second sentence is somewhat indirect ('this is how one reaches a molecule') but still earns its place by explaining why a sequence-less file is acceptable input.

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?

With an output schema, full annotation coverage, and fully documented parameters, most of the calling burden is carried elsewhere. What remains missing is the merge/replace semantics on the target record, which an agent needs before invoking a feature-writing tool a second time.

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% and the field descriptions are unusually rich (file/sequence refusal rules, coordinates_only claiming semantics). The description adds no parameter-level detail beyond restating that the source is a GTF, 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+resource: putting GTF features onto the open record, and explains that a GTF carries positions but no sequence, which frames why the tool exists. It does not name or contrast with nearby siblings such as annotate_region or auto_annotate, so an agent must infer the boundary.

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 clause 'this is how one reaches a molecule" from a GTF hints at when to use it, and the schema params carry explicit resolution rules (refuse-and-name behavior when multiple files or seqids exist). There is no explicit when-not or named alternative tool, so guidance is implied rather than stated.

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