emu_query_sql

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

With zero annotations, the description carries the full behavioral burden and the whitelist ('SELECT, WITH, and PRAGMA statements only') does real work, implicitly signaling a read-oriented surface. But it never actually labels the tool read-only or side-effect-free — a notable gap since certain SQLite PRAGMAs can mutate state — and it says nothing about error behavior, row limits, or query timeouts.

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, zero filler. The availability precondition is front-loaded ahead of the statement whitelist, and every clause earns its place. Nothing could be cut without losing information.

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 lightweight 2-param tool this is close to minimally viable: it states when the tool works, what statements are allowed, and scopes its behavior with 'only.' The gaps that hold it back are the unexplained 'params' semantics, the lack of any return-shape note, and no fallback guidance for the non-sqlite storage mode.

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% and the description offers zero parameter guidance. While the name 'sql' is self-evident, 'params' is genuinely opaque — the flat-array-of-primitives structure strongly implies positional bound parameters, but that concept is never stated, so an agent must guess at its semantics and whether it is optional.

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 provides a specific verb+resource (query SQL against the emulator storage) and adds meaningful scoping with a statement whitelist: 'Supports SELECT, WITH, and PRAGMA statements only.' This crisply distinguishes it from the ~70 sibling tools (many of which are dotted-path RPC emulators or structured read APIs), though it never names a sibling explicitly.

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 'Available when CUCM_EMULATOR_STORAGE=sqlite' conditional is a genuine, useful precondition that warns an agent the tool may be absent depending on environment. However, it provides no when-not-to-use guidance, no pointer to alternatives (e.g., 'prefer emu_get_evidence for structured access'), and no indication of what happens when the precondition is unmet.

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