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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: exactly one of three parameters must be supplied, name lookups with multiple matches return a refusal carrying a candidate list, and the tool deliberately excludes manager and sole-trader data. That negative scope and ambiguity protocol are exactly what 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?

The long field enumeration is dense but earns its place because no output schema exists. Structure is partly inverted: the field catalog dominates the first sentence while the more actionable parameter/ambiguity rules come later, so an agent skimming must read to the end.

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 return-value burden and does so thoroughly, plus covers parameter exclusivity and ambiguity handling. It omits what happens on zero results and gives no format hints for the identifier parameters.

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 coverage is only 33% (only org_id is documented), so the description has to compensate. It does so for the mutual-exclusivity rule across the three parameters and for the multiple-candidate failure path on 'название', but the ИНН and 'название' formats and matching rules remain unexplained.

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 names the resource precisely ('Сведения об образовательной организации') and enumerates the returned fields (ИНН, ОГРН, ОКТМО, license/accreditation status, programs, contacts, coordinates), which makes it unmistakably the organization-card tool rather than a search or ranking tool. It also states what it does not return (руководитель, ИП). No explicit verb and no reference to siblings, so it stops short of 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?

'Задаётся один из трёх параметров' tells the agent how to drive the tool, and the multiple-match refusal behavior is useful, but there is no statement of when to reach for this tool versus specialty, territory, or where_to_study. Usage is implied by the field list rather than stated.

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