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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description still adds real behavior beyond that: ordering ('newest first'), the meaning of the total count, the default/max limit, the substring-with-fallback location matching, and the normalization that an empty list is a normal result. Pagination and auth requirements are not addressed, leaving a modest gap.

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?

Front-loaded with the scope rule, then dense but information-carrying sentences on filters, ordering, and limits; there is essentially no filler. It is slightly long for a single paragraph, but every clause specifies a distinct behavior an agent needs.

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 eight-parameter filter tool with an output schema (so return values needn't be explained, though the 'total' semantics are a nice addition), the description covers scope, filters, ordering, and limits well. The only real omission is the archived-vs-active distinction, which the agent must pick up from the schema.

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?

Although schema coverage is reported as 0%, the description explains the semantics of the key filters: what fields 'query' spans (title, company, location, notes, description), how 'min_match' interacts with unanalyzed vacancies, and how 'location' falls back to the job description. It omits the 'archived' filter, which is only documented in the schema, so it does not fully compensate for the coverage gap.

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 the user's tracked vacancies') and immediately pins down scope that distinguishes it from siblings like get_recent_vacancies or get_vacancy_detail: only finished analyses and never-analyzed tracked vacancies are returned, while running/failed analyses are excluded. An agent can tell what belongs in the result set without opening a schema.

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?

The inclusion/exclusion rule ('analysis running or failed are not listed') and the note that min_match 'drops unanalyzed ones' give clear context for when this search is appropriate. It stops short of naming an alternative tool (e.g. get_recent_vacancies) or an explicit when-not-to-use condition, so it is strong context rather than full routing guidance.

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