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

Annotations already declare the safe, non-destructive, open-world profile, and the description adds real context beyond them: the table is built by counting annotated CDS of a RefSeq assembly with assembly/CDS-count provenance, and the call costs a network round-trip. The phrase 'LEAVES NOTHING' reads as reassurance that nothing outside the project changes, though the agent still isn't told what happens when the organism has no table (fallback vs. error).

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-loaded with the action and outcome in the first sentence, followed by source semantics and the handoff. The parenthetical in the second sentence and the standalone fragment about network round-trip are slightly dense/parenthetical-heavy, but each sentence earns its place.

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 present, return values need not be explained here, and the description still usefully points at `report.builtFrom`. It covers sources, provenance, persistence, and downstream consumption for a 7-parameter, nested-schema tool. The main omission is failure behavior for unmatched organisms or unusable `_files`/`_subject` combinations.

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 rich enum descriptions for mode/source/coverage and for organism resolution and save_as naming, so the schema carries the parameter burden. The prose adds the naming-handoff convention (`table`) and the builtFrom provenance link, but nothing the schema doesn't already say. Baseline 3 is appropriate.

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?

Specific verb+resource: fetch a codon-usage table for a named organism and persist it into the project under a name. It also disambiguates from the surrounding codon family by naming the consumers (`codon_usage_analysis`, `codon_optimality`) rather than leaving the agent to guess which sibling builds vs. consumes a table.

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?

Clear usage context: use this when later steps need to score against a table by name, and hand the saved name to the codon tools in `table`. It explains the ncbi-vs-kazusa selection (assembly available anywhere vs. mirror-only published tables). It stops short of explicit exclusions, e.g. when to count from project sequences or use `codon_usage_distance`/`discover_codon_outliers` instead of fetching.

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