query

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

No annotations are provided, so the description carries the full behavioral burden. It does add genuine value beyond structured fields: narrate's LLM 'only sees aggregates', spec means 'no LLM is used', and 'by' is persisted in the local query log. It stops short of stating read-only scope, auth, error behavior, or what 'evidence' actually contains.

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-loaded with a one-line purpose, followed by a compact per-parameter list with no filler. Slightly dense formatting (inline indented param notes) but every line earns its place.

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?

An output schema exists, so return values are covered and need not be explained. With no annotations, the description should carry the behavioral and routing load, but it omits sibling differentiation and the QuerySpec structure, leaving meaningful gaps for a 4-parameter tool.

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%, so the description must compensate; it does explain question, narrate, and by meaningfully (though 'by' restates the schema default). The critical 'spec' parameter is only described as 'optional structured QuerySpec' with no shape or pointer to list_schemas, leaving the agent unable to construct it.

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 states a recognizable action ('Answer a question') against a resource ('the record book') and flags that evidence is returned. However, 'record book' is undefined domain jargon, and the definition never distinguishes this from siblings like query_log, history, or get_entity, so an agent cannot cleanly route between them.

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?

There is no explicit when-to-use/when-not-to-use guidance relative to query_log, history, or get_entity. The only implied usage signal is the spec conditional (structured spec bypasses the LLM), which is a behavioral note rather than routing guidance.

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