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

Annotations already declare non-readonly, open-world, non-idempotent behavior, but the description adds substantial context beyond them: runs are real (not simulated), pinned to the specialty's model with no fallback, cost incurred on your keys, graded pass/fail, and the call is asynchronous ('returns at once with state qualifying'). It also discloses rate/ownership limits and accepted auth methods (JWT, rk_ key, MCP OAuth).

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?

Purpose is front-loaded in the first clause, and every sentence carries operational information (grading rule, model pinning, async return, read-back path, caps, auth). It is dense and somewhat run-on, but there is little pure filler to cut.

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 async, non-idempotent action with no output schema, the description covers what an agent needs: what the run does, that it returns immediately with a 'qualifying' state, and exactly where to read results (the specialties GET endpoint). Auth options and usage caps round out the picture.

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 0% across two required parameters, so the description must carry the semantic load. It only obliquely gestures at them ('one specialty', 'your own agents only') and never explains the expected format of agent_id or specialty_id or how they are obtained.

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 gives a specific verb and resource ('Start the qualification of one specialty') and details the mechanism: three real runs on the contract's example inputs, each graded pass/fail, 3/3 to prove. It is unmistakable what the tool does. However, it never distinguishes itself from closely named siblings such as agent_specialty_exam or house_specialty_qualify, so an agent must infer the difference.

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 states concrete operating conditions: one qualification at a time per agent, a daily cap per owner, and that it works only on your own agents. That gives a clear sense of when the call is valid. It stops short of naming an alternative tool or an explicit 'do not use this for X' exclusion.

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