schema_describe

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

No annotations are provided, so the description carries the full burden. It does disclose the important safety traits (PII removed, data is Faker-generated dummy rows, no real data returned), which is genuinely useful context, but says nothing about permissions, result size, or pagination.

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 core behavior is front-loaded in the first sentence, the no-real-data caveat follows immediately, and the single parameter is documented compactly. No filler.

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?

An output schema exists, so return values need not be described, and the single parameter is covered. The only real gap is routing guidance against the sql_run/fixture_make siblings, which is minor for such a narrow tool.

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 0% and there is one parameter, yet the description fully explains it: 'view' selects a specific view and defaults to all views when omitted. That compensates well for the undocumented schema, though it adds no format or naming-convention detail.

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+resource: it returns column definitions for the PII-stripped (claude) views plus Faker-generated dummy rows, and explicitly notes it does not return real data. This separates it from sql_run, though it never names that sibling directly.

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 'does not return real data' clause implies this is for schema inspection rather than querying, but there is no explicit when-to-use/when-not guidance and no mention of the obvious alternative sql_run or fixture_make. Usage is left to inference.

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