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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new context: queries are enforced SELECT-only, and returned rows may contain text typed by household members or external share-link users that must be treated as data, not instructions. It does not describe failure behavior for an undeclared query name or any result-size limits.

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?

Front-loads what the tool does, then the manifest constraint, then the untrusted-data warning — every sentence carries information. The final sentence is syntactically tangled ('text that household members, and through share links people outside the household, typed'), costing some immediate readability.

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?

With only two required params, rich annotations, and no output schema, the description supplies the two things the structured fields cannot: the manifest prerequisite and the data-versus-instructions safety rule. The main residual gap is the absence of any indication of result shape or size, which matters since there is no output schema.

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 50%: query_name is already documented in the schema and the description only reinforces the manifest-source constraint, while app_id is undocumented in both places. The description adds the useful 'must be declared in ai_access.db_exports' rule but does not compensate fully for the uncovered app_id parameter.

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 and resource ('Run a named read query against a DB-based app') and narrows it to SELECT-only queries declared in the ai_access.db_exports manifest, so the agent knows this is not an ad-hoc SQL interface. It never names a sibling such as get_app_data, so the boundary with the generic data-reading tool must be inferred.

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 a concrete prerequisite: the query name must already exist in the app's ai_access.db_exports manifest field, which tells the agent when this tool is applicable. It gives no explicit when-not condition or alternative for apps without declared exports (presumably get_app_data), leaving that inference to the agent.

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