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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's job is to explain semantics — and it does: verdict rules (strong = every criterion met, possible = none failed but some unknown, none = a criterion failed), how unanswered questions degrade a verdict, and what `missing` versus `questions` contain. It also discloses a real constraint ("don't promise a sale or a price") and the buyer-figure provenance (date checked plus Dataconto page), which is useful behavior beyond the annotations. It stops short of 5 because nothing is said about latency, cost, or failure modes for an unlisted/no-buyer case.

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?

Purpose is front-loaded in the first clause and no sentence is pure repetition. It is a single dense, comma-spliced paragraph that interleaves return-value documentation, unknowns behavior and presentation instructions, so the reader must work harder than a short structured version would require.

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 no output schema, the description carries the full burden of explaining returns, and it does: per-buyer verdicts, per-criterion states, miss reasons, buyer figures with dates and source page, plus `missing` and `questions`. The main remaining gap is the implicit dependency on a prior buyer-listing step, which matters for calling the tool correctly at all.

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 every enum value and nested `answers` field is documented inline, so the schema does the heavy lifting and the baseline of 3 applies. The description adds only a partial gloss — "each listed buyer's published criteria against the owner's answers" connects `answers` to its purpose — and says nothing about the required `side` switch (company vs code) that changes which answer fields are relevant.

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?

"Runs Dataconto's fit check: each listed buyer's published criteria against the owner's answers" is a specific verb-plus-resource statement with a clear input/output framing that an agent can grasp without opening the schema. It does not explicitly name a sibling (list_buyers, code_value, rights_check) to distinguish scope, which keeps it off a 5.

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?

Usage is only implied: the tool scores "listed" buyers and says unanswered questions count as unknown, so an agent can infer buyers must be listed first (presumably via list_buyers), but the description never states that prerequisite or when to prefer this over estimate or rights_check. There are no explicit when-not conditions; the only directive given is about answer completeness ("Answer what you know; leave the rest out") from the schema.

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