keyboard_mistypes

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real depth beyond that: it guarantees precision ('a hit is reported only when the remapped text is a query that really appears in the data') and warns that include_unmatched=True introduces false positives. That precision/precision-loss contract is exactly the kind of behavioral context annotations cannot convey.

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?

Front-loads the core concept in sentence one, then layers the precision rule and the parameter caveat. The illustrative example (rather than abstract prose) makes the definition compact and usable. Slightly dense, but every sentence adds 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?

The output schema exists, so return-value explanation is unnecessary, and the tool's core idea plus the layouts/flag semantics are covered. Still incomplete for a 9-parameter tool: no sibling routing and six parameters are left entirely unaddressed, so an agent must guess at date-range, source, and row-limit behavior.

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 coverage is 0% for 9 parameters, so the description must carry the load. It meaningfully documents only two: layouts (value list and what fa/fa2 mean) and include_unmatched. Key params such as days, source, search_type, max_rows, start_date, and end_date are undocumented in both schema and description, leaving most of the surface unexplained.

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 (queries typed on the wrong keyboard layout) and immediately grounds it with a concrete example ('ovdn lhadk' = «خرید ماشین»). This is clearly distinguishable from the sibling analysis tools (query_variants, language_breakdown, top_terms), so an agent can tell what class of finding this returns without opening the schema.

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 explains the include_unmatched tradeoff well ('more findings, some false positives'), which is genuine usage guidance for that flag. However, it never states when to reach for this tool over neighbors like query_variants or language_breakdown, and gives no prerequisites or scoping advice; usage is mostly implied by the concept.

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