get_germplasm_metadata

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that the tool reads server-stored attributes and writes a local file, and it discloses an edge case: sample_name is blank when callsets could not be read. It does not explicitly state whether the server data is mutated, but 'Reads the attributes already stored' strongly implies a read-only operation with a local file side effect.

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?

The description is front-loaded with the core purpose and output, then expands into the most decision-relevant usage details. Each section earns its place: the join guidance prevents a common failure mode, and the sibling exclusion is concise. Despite being long, it contains no 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?

The description covers the source of metadata, the output file format, row-level semantics, the join key, an important edge case, and the relevant alternative tool. Since an output schema is present, the description does not need to enumerate return fields, and it provides enough context for an agent to select and invoke the tool correctly.

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 schema already documents both parameters well, including the important warning about variant_set_db_id. The description adds context about the output file and the meaning of the data, but it does not add new parameter-level detail beyond what the schema provides. 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?

The description is specific and action-oriented: it 'Fetches server-stored per-individual metadata' and writes a CSV with one row per accession and attribute columns. It also distinguishes itself from the sibling tool search_callsets, which is for the sample/callset level, so an agent can tell them apart.

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 gives explicit guidance on when to use this tool versus the alternative: 'For the sample/callset level itself ... use search_callsets instead.' It also explains the prerequisite that metadata must have been imported via import_metadata or a BrAPI source, and provides detailed join instructions (join on sample_name, not germplasm_name; convert CSV to TSV for metadata_tsv; split semicolon-joined samples).

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