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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely non-obvious behavior: upstream filters only on free text, so biome_lineage is applied client-side over fetched pages, and the response reports how many rows were scanned. That partial-filter disclosure is the kind of operational quirk an agent cannot infer from structured fields.

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 purpose and the authoritative-use claim, then the preference over web search, then the filtering caveat. The environment-example list is slightly padded, but every sentence carries actionable routing or behavioral information.

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?

There is no output schema, and the description compensates by telling the agent what each hit carries (MGnify accession, controlled biome lineage, ENA project accessions) plus the scan-count reporting, which lets an agent judge result completeness. All three optional parameters are accounted for, so nothing needed to call it correctly is missing.

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 schema already documents ranges, defaults, and examples, so baseline is 3. The description adds selection-level value by confirming that biome_lineage is a client-side post-filter and pointing to mgnify_biomes for valid lineage strings, though most parameter detail is duplicated from the schema rather than extended.

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 ('Search MGnify for public metagenomics studies') and immediately scopes it by defining what a study is (assembled, annotated microbiome sequencing projects). The qualification 'AUTHORITATIVE for what microbiome studies exist for this environment or host' with concrete examples (human gut, soil, marine, wastewater, coral, chicken caecum) makes it unmistakable versus siblings mgnify_study, mgnify_biomes, and mgnify_genomes.

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?

Explicitly states when to use it ('AUTHORITATIVE for what microbiome studies exist for this environment or host') and when not to — 'PREFER OVER WEB SEARCH' with the reason (accession + biome lineage + ENA project accessions in each hit). It also routes the agent to the sibling mgnify_biomes for exact lineage strings.

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