Varrd

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

Beyond annotations (destructiveHint=true, idempotentHint=true), description adds valuable behavioral context: it discloses cost ('no credits consumed'), specifies error conditions triggering use ('stuck', 'bad state'), and explains the post-reset workflow. Could explicitly confirm idempotency, but otherwise rich.

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?

Three sentences, optimally structured: (1) action/purpose, (2) usage conditions and cost, (3) next steps. No redundancy or filler; every clause earns 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?

Comprehensive for a session management tool: covers failure modes, cost, destructiveness, and recovery workflow. Given the simple schema (1 param) and good annotations, this adequately prepares the agent. Missing only explicit mention of data loss implications or return value, but destructiveHint=true covers safety profile.

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 100% with clear parameter description ('The session_id to reset'). Description implies the parameter through context ('resetting') but does not add additional semantic detail beyond the schema. Baseline 3 appropriate for complete schema coverage.

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?

Description states specific action ('Kill') and resource ('broken research session') with clear outcome ('start fresh'). It distinguishes from sibling 'research' tool by specifying this is for error recovery/stuck states rather than normal operation.

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?

Explicitly states when to use ('when a session gets stuck, produces errors, or enters a bad state') and provides clear workflow guidance ('After resetting, call research without a session_id'). Also notes cost implications ('Free — no credits consumed') to inform the decision.

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