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

Annotations already declare readOnlyHint=true, destructiveHint=false, and closed-world scope. The description adds meaningful behavioral context beyond that: results are filtered to permitted tables/columns/relations, and it explicitly guarantees no sample rows are returned. It does not, however, discuss pagination or error behavior on a non-permitted table.

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 sentence covering scope, returned fields, and a negative guarantee, with no wasted wording. The most important constraint ('schema only, never sample rows') is placed last for emphasis and is easy to scan.

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 re-explained, and the description still usefully previews them. Given only two schema-documented params and read-only annotations, the definition is essentially complete; the only omission is guidance on behavior when the table is not permitted.

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%, so both parameters and their provenance (list_tables, list_sources) are already documented in the schema. The description adds the 'permitted table' constraint but no new syntax or format guidance, so the baseline of 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?

States a specific verb (describe) plus resource (table) and enumerates exactly what is returned: metadata, permitted columns, PostgreSQL types, nullability, keys, and permitted relations. It also implicitly separates itself from query_table by specifying 'schema only and never sample rows'.

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?

Usage is implied rather than stated: an agent can infer this is the introspection tool versus query_table for data, and 'one permitted table' hints at permission scoping. But no sibling is named and no explicit when-to-use or precondition (e.g., table must exist in list_tables output) is spelled out.

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