find_tables

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

With no annotations, the description carries full burden. It thoroughly explains caching behavior (auto-refreshes with auth, uses cached data if available), case-insensitive search, and the two return modes (flat list vs compact summary). It also justifies why comment and column count are omitted. However, it does not explicitly state that the tool is read-only, though this is implied by the search operation.

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?

The description is well-structured with clear sections (USE THIS WHEN, RETURNS, HOW IT WORKS, Parameters, Examples). It is thorough without being verbose; every sentence adds value—explaining return modes, caching, search behavior, and example usage. Front-loaded with the main purpose.

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?

The tool has two distinct return modes, caching behavior, and auth requirements. Despite lack of output schema, the description fully covers both response formats, explains when each is triggered, provides narrowing guidance, and describes caching mechanics. It is complete for effective use.

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 0% for the single parameter, so the description must compensate. It adds that search_term is a keyword, case-insensitive, and provides three examples. This gives sufficient meaning beyond the schema's title and type, meeting the baseline of 4 for a single parameter with no schema docs.

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?

Clearly states the tool searches for tables by keyword across ALL databases, distinguishing it from siblings like show_tables (which filters by database/schema patterns) and describe_table (which provides details). The description specifies verb 'search', resource 'tables', and scope 'all databases'.

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?

Explicit 'USE THIS WHEN' section advises using this tool when you don't know the table's location but know part of its name or purpose. It also provides narrowing guidance via the 'spilled' hint and recommends using show_tables with more specific patterns, thus clearly indicating when to use alternatives.

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