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

With no annotations, the description carries the full burden and does most of it well: it discloses that validation is structural (not string matching), the exact rejection triggers, and that refusals name the rule hit. It omits auth/permission requirements and any return-shape expectations, which for a mutation-free read tool is a modest gap.

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 tightly written sentences with zero filler; the core capability is front-loaded and the enforcement details follow immediately, each earning 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?

For a two-param read tool with no output schema and no annotations, the description covers the critical enforcement behavior an agent needs. It stops short of describing the result shape or column/error payload structure, which leaves a small completeness gap.

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 100%, so both params (sql, tenant_key) are already fully documented in the schema. The description largely restates the sql constraint rather than adding semantics, so the baseline 3 applies.

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 single read-only SQL SELECT (CTEs allowed)') and scopes it to 'this tenant's own tables.' It does not, however, differentiate itself from the very similar sibling host.state.query, so the agent must infer which query surface to use.

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 defines operational bounds (exactly one SELECT, 1,000-row cap, 5-second timeout) which implicitly tells the agent when the tool will refuse, but it gives no explicit when-to-use vs. when-to-prefer-an-alternative guidance against siblings like host.state.query or host.table.append.

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