describe_object

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 discloses that the operation is cheap/read-only, that row counts are approximate (from reltuples, not exact), and enumerates the full scope of what's returned. This is strong transparency for an introspection tool with zero annotation support.

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?

Three sentences, all high-value: what it returns, cost signal, and when to use. Front-loaded with the core purpose, no wasted words.

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?

There is an output schema (covering return values), so the description need not enumerate the response format. The tool is simple (2 params, no nesting) and the description fully covers behavioral caveats (approximate count, cheap) and usage context. Nothing substantive is missing.

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 0% for two trivial parameters (schema, name). The description explains what the tool does but doesn't elaborate on the parameters themselves beyond what's obvious from their names and types. However, for introspection tools, schema and name are self-evident; the baseline 3 is acceptable since the description doesn't add semantics the names don't already convey.

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?

Specific verb+resource: 'Describe one relation' followed by an exhaustive enumeration of what it returns (columns, PK, FKs both directions, indexes, constraints, row count). Clearly distinguishes from siblings like execute_query and list_objects by being a dedicated introspection tool.

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?

Provides explicit guidance: 'Prefer this over querying catalogs by hand; use it before writing queries against unfamiliar tables.' Also notes cheapness ('Cheap'), giving clear cost-based rationale for use. Mentions pg_class.reltuples for approximate counts, setting expectations.

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