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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds genuinely new behavioral context: the query is submitted to a third party and the sequence leaves the local machine, plus the tool emits hits, a tabular report and a job id for downstream use. It stops short of describing asynchronous job lifecycle, expected queue/runtime, or that a contact email is mandatory — the latter only surfaces in the schema.

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 sentences, front-loaded with the action and service, then outcome, then the uppercase data-egress warning in the position where it will be read. No sentence is filler and nothing is buried.

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 and annotations covering safety, the description need not explain return values, and it still signals the returned artifacts. What remains unstated — async job polling, timeouts, and the fact that a contact email is effectively required — is a modest omission for a remote submission tool.

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%, including per-parameter notes on program alphabet derivation, region/feature coupling, database defaults and the free-form `parameters` passthrough, so the schema carries the semantics. The description adds only the parenthetical program list, which duplicates the enum, and does not explain the empty-sequence/region fallback beyond what the schema already states.

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 a sequence against NCBI BLAST+ at EMBL-EBI' — and enumerates the five programs and the target databases (ENA, UniProtKB, PDB, vector-screening sets). It is clearly distinct from local/project search tools because it names a remote service, but it never explicitly contrasts itself with the many BLAST-family siblings (ebi_align, blast_project_sequences, delta_blast_smart, rps_blast_smart, rpstblastn_smart), leaving that routing to inference.

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?

Implied usage is clear (turn an unnamed span into named homologues for a methods section), and 'The sequence LEAVES THE MACHINE' is a real decision signal about external submission. However, there is no explicit when-not guidance and no alternative named, which is a notable gap given roughly a dozen alignment/BLAST siblings that could be selected instead.

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