update_vacancy

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 provided. The description does add real value beyond them by stating that only the fields passed are modified, which clarifies partial-update behavior and reassures the agent that omitted fields will not be wiped. It does not, however, say what is returned, whether hidden=true has side effects, or how conflicts/validation errors surface.

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, zero filler, with the action and its field scope front-loaded ahead of the partial-update caveat. Nothing is redundant or padded.

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?

Twelve parameters with no output schema and only three annotations put real weight on the description, and it covers roughly what a patch tool minimally needs (which fields, only-passed-fields semantics). It omits return shape, error behavior, and any hint that account_division/account_region interplay with company, which a 12-parameter mutation tool could reasonably mention.

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 every one of the 12 parameters already carries its own Russian documentation (HTML formats, priority enum 0/1, the note that company is ignored when divisions are enabled). The description only echoes four field names and adds no format or constraint detail beyond the schema, which is baseline-3 territory.

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 verb 'Изменить' plus the resource 'поля вакансии' is specific, and the parenthetical enumerates four concrete fields (название, зарплата, описание, приоритет). It is clearly distinguishable from create_vacancy/get_vacancy by name and verb. It stops short of a 5 because the enumeration covers only part of the updatable surface (body, conditions, requirements, hidden, division, region are absent), so the reader cannot tell whether the tool is broader than the examples suggest.

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?

There is no explicit when-to-use or when-not-to-use statement and no mention of prerequisites, though the existence of create_vacancy, get_vacancy and set_vacancy_state beside it makes routing plausible. The only guidance-like element is the patch semantics sentence, which implies 'use this to change a subset of fields on an existing vacancy'. Adequate but entirely inferential.

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