query_sql

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

The description goes far beyond the readOnlyHint annotation: it warns the cache is session-scoped and disappears when the session ends, reports that sync tables are only populated by explicit sync calls, and discloses that set_company empties every SQL table when the active company changes. This prevents an agent from silently querying stale or cross-company rows. The readOnlyHint=true annotation is consistent with the read-only SELECT description.

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 dense but front-loaded with the most important behavior: read-only, in-memory cache. Each clause about table population and lifecycle earns its place, though the long table-schema listing and the trailing set_company detail make it longer than strictly minimal. It is informative without being padded.

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 query tool with one parameter and no output schema, the description covers the full lifecycle: what is in the cache, how each table gets populated, which data can be derived without a separate report tool, and what invalidates the data. The agent has enough context to decide when to call it, what to run, and what to expect after session/company changes.

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?

The input schema already fully documents the single 'sql' parameter as 'A single SELECT statement' (100% schema description coverage). The description adds useful table context but does not add much parameter-level semantic detail such as syntax restrictions, limits, or examples. Baseline 3 is appropriate because the schema carries the parameter-documentation burden.

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 opens with a crisp specific action — 'Run a read-only SQL SELECT query against this session's in-memory cache' — and immediately distinguishes it from the report getter siblings. Listing the exact tables and how they are populated removes ambiguity about what this tool can query.

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?

The description explicitly explains when to use query_sql vs the domain get_* report tools: after a report call, a follow-up question can query the refreshed table here instead of re-fetching from Tally. It also tells the agent when NOT to rely on it — the five report tables only hold the most recent call's data, and re-calling the report tool is needed for a different period. This is strong routing guidance.

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