inspect_schema

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

With no annotations, the description carries the transparency burden. It discloses a key safety trait ('Read-only') and adds nuance with 'actually applied'—implying it reflects real database state rather than just migration files. This goes beyond a simple read hint, though it doesn't detail potential errors or permissions.

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?

Two sentences with zero filler. Front-loads the action and purpose, then adds a crucial safety qualifier. Every word 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?

For a simple read-only inspection tool, the description covers the essential aspects: action, target, output, and safety. There is no output schema, but the return value is implied. It could mention column detail specifics, but is sufficiently complete for its simplicity.

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 coverage is 100% with clear descriptions for both `db` and `table`. The description reinforces the optional scope but adds no new semantic meaning beyond what the schema already provides. Baseline of 3 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 clearly states a specific action ('Query the local D1 `sqlite_master`'), a concrete resource (sqlite_master), and the exact output ('list every table + the column definitions actually applied'). This distinguishes it from sibling tools like `query_d1` or `list_models`, making the purpose unmistakable.

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 implies usage: when you need to inspect actual table definitions. However, it does not explicitly state when to prefer this over alternatives or provide exclusions. Sibling tools like `query_d1` could theoretically do similar, but no comparison is offered.

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