sync_to_sql

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

Annotations only provide readOnlyHint=true and openWorldHint=false, so the description carries the behavioral burden and delivers: the cache is in-memory and session-scoped, is gone when the session ends, and is replaced on company switch/re-sync so nothing lingers between companies. It also discloses the scope boundary (no vouchers). The readOnlyHint is consistent — Tally itself is never modified.

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?

Two sentences, front-loaded with the action verb and resource, followed by dense but relevant qualifiers (session lifetime, company-switch invalidation). The exclusion-and-alternative sentence earns its place by preventing a likely misuse. No filler and no repetition of schema or annotation content.

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 0-param tool with no output schema, the description covers the essentials: scope of data, cache semantics, lifetime, invalidation on company switch, and sibling routing. The only gap is no statement of what the tool returns or how the agent detects a successful sync, which a brief note would close.

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 is empty with 0 parameters, so the baseline is 4 and there is nothing to document. The description compensates by clarifying what the operation covers (ledgers, groups, stock items) and its exclusions, effectively serving as the parameter contract for a parameterless tool.

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 specific verb and resource ('Pull ledgers, groups, and stock items from TallyPrime into this session's SQL cache'), stating exactly what the tool does and where the data goes. It explicitly differentiates from the sibling sync_vouchers_to_sql by naming what it does NOT cover, so an agent can disambiguate without opening schemas.

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?

It states the motivating use case ('so query_sql can run fast arbitrary queries without hitting Tally each time'), telling the agent when this tool is valuable. It gives an explicit when-not: 'Does NOT sync vouchers — use sync_vouchers_to_sql for those, one date range at a time,' naming the alternative and a usage qualifier. This is explicit when/when-not/alternative guidance.

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