llmconveyors-mcp

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

With no annotations provided, the description carries the full disclosure burden and delivers comprehensive behavioral context: credit consumption ('50-500 credits'), rate limits ('10 req/min'), authorization scope ('sales:write'), and stateful execution patterns ('continue a previous run'). It details side effects and operational constraints beyond what structured fields provide.

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?

At approximately 70 words, every sentence earns its place: purpose statement, phased execution controls, sibling coordination, resource constraints, auth requirements, and prerequisites. Information is front-loaded and uses efficient punctuation to separate distinct operational concerns without fluff.

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?

Given the tool's complexity (21 parameters, agent-based stateful execution, no output schema), the description adequately covers the operational lifecycle: initiation, phased execution gates, polling mechanisms, and prerequisite checks. It compensates for the lack of output schema by documenting the interaction pattern (agent-status polling).

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%, establishing a baseline of 3. The description adds significant workflow context for key execution parameters (explaining what 'autoSelectContacts=false' and 'autoApproveDraft=false' achieve in practice) and documents cost/rate-limit parameters not present in the input schema. It does not redundantly document all 21 parameters, which is appropriate given the comprehensive schema.

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 opens with a specific verb-resource pair ('Run the B2B Sales agent') and clearly scopes the functionality ('researches a company and generates personalized sales outreach'). It effectively distinguishes this from siblings like 'job-hunter-run' (different domain) and 'agent-interact'/'agent-status' (supporting tools rather than the main execution).

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 documents phased execution controls ('set autoSelectContacts=false to pause'), specifies the polling workflow ('Poll with agent-status, respond with agent-interact'), and states prerequisites ('Check balance with settings-usage-summary before running'). This provides clear when-to-use guidance and prerequisite checks.

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