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

Annotations already declare read-only, idempotent, open-world and non-destructive, so the safety profile is covered. The description earns credit by disclosing a non-obvious operational quirk: free-text search runs upstream while catalogue_id and taxon_lineage are applied client-side 'over the fetched pages' because upstream silently ignores them — a real filtering gotcha the schema does not convey.

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 dense sentences, front-loaded with capability, then authority/use-case, then the filtering caveat. There is no filler; every clause (hit fields, comparison to web search, upstream/client-side split) carries information an agent needs.

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 100% schema coverage, full annotations and no output schema, the description supplies everything needed to call it correctly: capability, alternative, hit fields and the client-side filtering caveat. It falls short of 5 only because return shape/pagination is unaddressed and the relationship to the other mgnify_* tools is left implicit.

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 baseline is 3. The description goes beyond the schema by explaining which filters execute upstream versus client-side and why, which affects how an agent should combine limit with the client-side filters. It adds operational meaning rather than repeating field docs.

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 gives a specific verb and resource ('Search MGnify's species-level genome catalogues'), quantifies the scope (~57,000 MAGs/isolates) and lists the biomes covered. It clearly separates itself from web search, but never distinguishes itself from its own mgnify_biomes / mgnify_search_studies / mgnify_study siblings, so an agent still has to infer the division of labor among the MGnify family.

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?

It states explicit use cases ('AUTHORITATIVE for "is there a genome for this uncultured taxon" and for MAG quality questions') and an explicit alternative ('PREFER OVER WEB SEARCH for microbial genome-catalogue lookups'). What is missing is the when-not / sibling routing: no guidance on when to reach for mgnify_biomes or mgnify_search_studies instead.

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