update_applicant

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered by structured data. The description adds one genuinely useful behavioral fact beyond them — that only the fields passed are modified, i.e. partial-update semantics — but says nothing about how empty/null values behave, whether omitted fields are preserved or cleared, required permissions, or what the call returns.

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?

Two short sentences with the partial-update rule front-loaded right after the verb, so the most misuse-preventing fact is not buried. The parenthetical field list is partly redundant with the schema's parameter descriptions, which is the only real waste.

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?

For an 11-parameter mutation tool with no output schema, the description is minimally adequate: it conveys intent and partial-update behavior but omits return/error behavior and does not surface the two required identifiers (account_id, applicant_id) or any permission expectations. Nothing is misleading, but an agent still needs the schema to call it safely.

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 all 11 parameters (including email, phone, money, birthday with its YYYY-MM-DD pattern) are documented in the schema itself. The description only names four field families, which the schema already covers in more detail, so it adds no syntax, format, or validation meaning beyond the structured data. Baseline 3 applies when the schema carries the semantics.

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 opens with a specific verb+resource pair ('Изменить поля кандидата') and enumerates the field families covered (name, contacts, position, salary), so an agent can immediately tell this is a partial field update on an existing applicant rather than a create or status-change operation. It stops short of naming any sibling, so differentiation from create_applicant or set_applicant_tags is inferred rather than stated.

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: 'Изменить поля кандидата' signals editing an existing candidate's attributes, and the second sentence warns that only supplied fields are touched. There is no explicit when-to-use vs. when-not guidance, no mention of prerequisites (e.g. the applicant must already exist), and no routing to alternatives such as change_applicant_status or set_applicant_tags for non-field updates.

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