Find tables, views, and columns by partial name or comment to avoid paging list_tables; returns up to 100 matches across readable schemas.
Find tables, views and columns by a piece of name or comment; use it instead of paging list_tables. At most 100 matches.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Part of a name or comment, e.g. "order". | |
| schema | No | Schema to look in; omit for every readable schema. |
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds one genuinely useful behavioral fact, the 100-match cap, but says nothing about ordering, truncation signaling, or what a match record contains. One extra detail against an already-declared safety profile lands at a 3.
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 sentence front-loads what is searched, then tacks on the routing hint and the result cap. No filler, nothing buried.
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?
No output schema exists, so the description should describe results; it names the resource types returned and the cap, which covers the essentials. Ordering and whether the cap is signaled to the caller are the remaining gaps.
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, including the "omit for every readable schema" default, are already documented in the schema. The description's phrasing of "a piece of name or comment" restates the parameter without adding substring/case-sensitivity semantics.
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 (find) plus the exact resources searched (tables, views, columns) and the match key (name or comment). It also names the sibling it replaces for this job, so an agent can separate it from list_tables without reading either schema.
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?
"Use it instead of paging list_tables" gives an explicit alternative and the condition that selects it. It stops short of covering the other siblings (describe_table, sample_rows) which would be the natural follow-ups once a match is found.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.