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

Beyond the annotations (which only cover safety: readOnly, idempotent, non-destructive), the description discloses two high-value behavioral traits: the monitoring is not fully joined to the registry, so 'no data' is a frequent and honest result rather than a claim about graduates, and the tool takes roughly one second (slowest in the set). These materially affect how an agent should interpret output and budget latency.

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 what the tool returns, then the cardinality constraint, then the result-shape distinction, then the honesty caveat and latency note. Dense but every sentence carries information; no filler.

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 burden of describing returns, and it does so explicitly (four metrics plus the two breakdown dimensions). It also covers the input constraint, the data-quality caveat, and performance, leaving nothing essential for a correct call missing.

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?

With only 50% schema coverage (специальность is undocumented in the schema), the description compensates: it explains that организация accepts INN or internal number and специальность accepts a code or name, and — more importantly — that the two parameters produce different result granularities (breakdown by specialty vs by country with organization counts). This adds real meaning beyond the schema.

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 a specific resource — cohort outcomes under employment monitoring — and enumerates the returned fields (graduation year, graduate count, employed share, median salary), so an agent knows precisely what data comes back. It also describes the two distinct operating modes (organization vs specialty) with different granularity. However, it does not explicitly contrast itself with siblings like cohort_forecast or where_to_study, so sibling differentiation is left implicit.

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?

It gives a hard usage constraint — exactly one of organization or specialty must be supplied — which directly guides invocation. It also warns about the 'no data' caveat and that this is the slowest tool in the set, a useful selection consideration. It stops short of naming when a sibling tool would be preferred instead.

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