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

With no annotations provided, the description fully carries the behavioral burden. It discloses API key requirements, cost/quota implications, latency, no-free-trial policy, and the exact behavior when a key is missing (returns a subscription URL to pass verbatim). It also warns against guessing keys, covering failure modes and side effects comprehensively.

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?

The description uses clear section headers (USE WHEN, DO NOT USE WHEN, REQUIRES, COST, LATENCY) that front-load the most actionable information. Each sentence earns its place, and the structure makes scanning effortless without unnecessary verbosity.

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?

Given the tool's complexity (external API, authentication, costs, multiple return values), the description covers what it does, when to use/avoid it, requirements, cost, latency, and return values. It, also, clarifies integration with score_prompt and handles the missing-key scenario. No output schema exists, so the explicit listing of return values is essential and well covered.

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?

The input schema already provides 100% description coverage for both parameters, so the baseline is 3. The description adds meaningful context for api_key by explaining why it is required, the subscription model, and the no-trial policy, which is valuable beyond the schema's format hints. However, it does not add anything for the 'prompt' parameter beyond what the schema states, so a modest 4 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?

The description opens with a specific verb+resource statement: 'Rewrite a prompt to score higher on the PQS rubric' and clearly enumerates the return values (optimized prompt, original/optimized PQS scores, side-by-side outputs). It distinguishes itself from the sibling tool score_prompt by including 'AND show before/after output comparisons', making the purpose unambiguous.

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 'USE WHEN' section lists four concrete trigger scenarios, including 'user got a low score from score_prompt' and explicit user requests. The 'DO NOT USE WHEN' section provides clear exclusions and names the alternative (score_prompt or direct writing). This is exemplary guidance for an agent deciding between tools.

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