Query CSV (SQL-like)

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety burden is lifted. The description adds genuinely new behavior: numeric-aware comparisons and a hard 1000-row return cap, both of which affect how an agent writes and interprets a query.

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 dense sentences, front-loaded with the core capability, then the two behavioral facts that matter most (numeric comparison, row cap). No filler or restatement of the name.

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?

With no output schema, the description carries return-shape duty and does so by stating the 1000-row ceiling. It leaves the default limit of 100 to the schema and says nothing about error behavior for missing files or bad columns, which is a modest gap for a read query 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?

At 57% schema coverage, the description compensates by naming the role of nearly every parameter (columns, WHERE conditions, ORDER BY, DISTINCT, LIMIT/OFFSET). 'Numeric-aware comparisons' adds real semantic meaning about how the op/value pairs behave, beyond the raw enum.

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 (SQL-like SELECT over a CSV) and enumerates the operations it supports (select/where/order by/distinct/limit). This lets an agent separate it from aggregating siblings like group_by or pivot_table by inference, but it never names an alternative 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?

Usage is implied by 'SQL-like SELECT' — row-level filtering and projection — but there is no explicit when-to-use statement and no routing to summarize_csv, group_by, or pivot_table for aggregated views. An agent reading only this must infer the boundary itself.

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