Know what's weak in your skill before you ship it: 9-dim score → total + rating + weak points + bands. Costs 5 QYY. Pass qy_token (Bearer from POST /ai/register). Returns qy_balance.
| Name | Required | Description | Default |
|---|---|---|---|
| qy | No | Your QY display id (e.g. QY... ) for attribution/logging | |
| qy_token | Yes | Your QY Bearer token (from POST /ai/register). The 5 QYY is deducted from this account. | |
| skill_text | Yes | The experience / Skill.md content to score (full text) |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does meaningful work: it discloses a 5 QYY cost, the auth requirement (qy_token as Bearer from POST /ai/register), and that qy_balance is returned. It does not cover failure behavior or whether anything is mutated server-side, keeping it short of a 5.
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 value proposition, then output shape, then cost and auth in a compact flow with no filler. The arrow notation is terse and slightly cryptic, but each clause earns its place.
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 still names the key return values (total, rating, weak points, bands, qy_balance) and the prerequisite (qy_token). Cost and auth prerequisites are covered, leaving only edge/failure behavior unstated.
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 the schema already documents qy, qy_token, and skill_text in detail. The description only reaffirms qy_token's role and adds the balance deduction context, so baseline 3 is appropriate.
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 (assess/score) and resource (a skill's text), and enumerates the output shape: '9-dim score → total + rating + weak points + bands.' It is clear what the tool does, though it doesn't explicitly name or contrast with siblings like get_rubric or recommend_skill.
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?
'before you ship it' implies a usage moment, but there is no explicit when-to-use/when-not guidance and no mention of alternatives such as get_rubric. The cost disclosure ('Costs 5 QYY') gives a reason to consider it deliberately, but that is not the same as routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.