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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful context about the diagnostic purpose (confirming deployed schema) and the exact fields returned, which adds value beyond the annotation. However, it doesn't discuss rate limits, caching behavior, or freshness guarantees of the returned data itself.

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?

Single dense paragraph, front-loaded with the core purpose and return fields, then a well-integrated usage scenario. Slightly longer than the TDQS-high example but every sentence earns its place — the troubleshooting scenario is genuinely instructive rather than padding.

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?

The tool has an output schema (so return format is already documented), zero parameters, and readOnly annotation. The description adds the operational context — how to use this diagnostic to distinguish stale-cache issues from real deployment gaps — which fully rounds out the tool's purpose for an agent. Nothing critical is 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?

Zero parameters, so the description has no parameter burden to carry. The baseline for 0 params is 4, and the description goes further by explaining what the return value semantically means (confirming the live deployed schema) and why each field matters (schema_hash comparison for stale manifest detection).

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?

Description uses specific verb+resource: 'returns exactly what build is live right now' with an explicit enumerated list of return fields. Clearly distinguishes from siblings by being a zero-argument diagnostic tool, distinct from functional tools like accessibility_check or palette_extract.

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?

Provides explicit when-to-use guidance ('if a tool you expect seems to be missing, call this first'), a concrete troubleshooting scenario, and even explains how to interpret results (compare schema_hash against another connection to detect stale cached manifests). Names the alternative interpretation to avoid ('before assuming the server is wrong').

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