Score portal quality (blocks + pages, with baseline delta)

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description reveals that scratch-marked records are excluded, that it compares against a baseline when version control is on, and that 100 has a specific meaning. These are meaningful behavioral traits not covered by annotations. It does not mention potential side effects beyond baseline updates, but the annotations reduce the burden.

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 is a single dense paragraph that packs essential information without fluff. Every sentence contributes: scope, exclusions, baseline behavior, and the meaning of 100. It is slightly long but well-organized, with the core purpose front-loaded. The structure is functional, though it could be broken into list form for easier scanning.

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 there is no output schema, the description implicitly states what the tool returns (scores and baseline deltas). It covers key prerequisites like version control on for baseline, and mentions the detail_below behavior. It doesn't explicitly state the output format or error handling, but for a scoring tool with simple boolean and integer parameters, the information is largely sufficient to invoke it correctly.

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 schema already documents both parameters fully (coverage 100%), so the baseline is 3. The description adds extra meaning for update_baseline by explaining the loop discipline and when to set it to true, which goes beyond the schema's simple 'save as baseline' note. However, it duplicates the detail_below description from the schema, so the net addition is moderate.

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 clearly states the tool's function: 'Score every block and page 0–100 on what is MECHANICALLY checkable' with a specific list of checks. It distinguishes itself from siblings by excluding scratch-marked records and referencing cleanup_scratch, and clarifies that 100 does not mean 'well designed' – a key scope distinction.

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 provides context on when to use the tool (for mechanical scoring) and when not to (scratch records go to cleanup_scratch). It also explains the loop discipline 'score, improve, re-score, and only update_baseline=true after a verified improvement', which guides the agent on when to set the baseline parameter. However, it does not explicitly compare with validate_portal or other similar validation tools, so alternatives are only partially addressed.

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