find_dead_weight

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the tool is non-destructive ('does not drop anything and never will'), which is key safety information. It also warns about the stats_since window causing false positives, and mentions the pgstattuple dependency. This is rich behavioral context, though it could go further (e.g., auth requirements, but that's likely shared across siblings).

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 concise and front-loaded: the first sentence immediately states the tool's purpose and what it finds. The second paragraph adds essential caveats (non-destructive, stats_since) without unnecessary fluff. Every sentence 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?

The description is fairly complete for a read-only analysis tool. It covers the tool's scope, safety profile, and a key caveat (stats_since). The output schema exists, so return values are already documented. It doesn't explain the profile parameter, but that's a minor gap given the overall context.

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 has one parameter 'profile' with zero description coverage. The tool description does not explain what 'profile' means, its format, or how it relates to the tool's function. Given the low schema coverage, the description should compensate but doesn't, leaving the agent to guess or infer from sibling tools like list_profiles.

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 purpose: 'Find indexes that cost writes but earn nothing' and enumerates specific categories (never-scanned, exact duplicates, prefix-redundant pairs, low leaf density). This specific verb+resource combination distinguishes it from sibling tools like list_hotspots or explain_query.

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 description provides clear context for use: these are observations, safe quick wins for review. It also gives a caution about stats_since and clarifies that pgverdict never drops anything. However, it doesn't explicitly name alternatives or state when not to use this tool versus siblings, so it lacks full exclusion/alternative guidance.

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