describe_table

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. With no output schema, the description earns credit for itemizing the return payload (columns, keys, referencing tables, indexes), which is real information an agent cannot get from structured fields. It does not say what happens for a nonexistent or ambiguous table, which keeps it below a 5.

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?

A single dense clause with no filler, front-loading the most commonly needed information (columns with types). It is a sentence fragment rather than a structured statement of purpose, which slightly limits immediate scanability.

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 low-complexity, two-parameter read-only tool with full schema coverage, the description covers what the caller needs to know about the return contents even without an output schema. Missing only edge-case behavior such as errors for missing tables and whether output is truncated for very wide tables.

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 100%, with both 'table' (accepting 'orders' or 'sales.orders') and 'schema' documented in the schema itself. The description adds nothing about parameter behavior or interactions, so the baseline 3 applies.

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 enumerates exactly what the tool retrieves: column types, NOT NULL flags, defaults, comments, keys, referencing tables and indexes. It is clearly distinct from siblings like list_tables, search_schema and sample_rows. It stops short of a stated verb+resource framing, relying on the tool name to supply 'describe', so it is clear but not fully self-contained.

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?

There is no explicit guidance on when to use this versus search_schema or sample_rows, and no stated preconditions. The schema hint about omitting 'schema' to scan every readable schema is the only usage-adjacent signal, and that lives in the parameter schema rather than the description.

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