introspect_connection

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

Description adds value beyond annotations by explaining the caching mechanism, idempotency, and dependency chain (cache read by list_tables, describe_table, get_semantic_context). Returns counts of cached objects and embeddings. Consistent with idempotentHint=true and readOnlyHint=false.

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?

Five concise sentences, each earning its place: purpose, when to use, idempotency, dependency, return value. Front-loaded with the main action, 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?

For a simple tool with no output schema, the description explains caching, usage timing, return values, and dependencies. Could briefly mention error handling or timeout potential, but overall fairly complete given the tool's simplicity.

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%, so baseline is 3. The tool description does not add new parameter information beyond what the schema already provides (connection and generate_embeddings). No extra semantics added.

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 clearly states it reads and caches database structure (tables, columns, foreign keys). It distinguishes itself from sibling tools like list_tables and describe_table by explaining they read from this tool's cache, establishing it as a prerequisite.

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?

Explicitly advises to 'Run once per connection before querying, and again after the schema changes', giving clear when-to-use context. Does not mention when not to use or provide alternatives, but the usage context is strong.

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