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

Annotations already declare read-only, non-destructive behavior, and the description adds substantial context beyond that: the hard size limit and its rationale, the fact that rows are sent directly and scored server-side with the full result returned, the optional touches/stage_history improving model quality, and the 'do not invent scores' constraint. This gives the agent clear operational expectations.

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?

The description is dense and front-loaded with purpose, then size constraints, data requirements, and return outputs. It is longer than average but the tool is complex with 15 parameters; however, it slightly repeats the 500-lead limit across two sentences and could be trimmed without losing meaning.

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 (15 params) and the presence of an output schema, the description provides the essential context: data prerequisites, size limit with alternative tool, optional inputs that improve quality, and a summary of returned artifacts. It explains when not to use it and what behavior to expect, making it complete for an agent.

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?

Input schema coverage is 100%, so parameters are already well-documented. The description adds minor semantic value by naming the essential lead fields (lead_id, created_date) and noting that touches and stage_history improve attribution, but it largely repeats schema information. Baseline 3 is appropriate.

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 'Scores' and names the exact resource ('open sales pipeline of 500 lead rows OR FEWER'), followed by the concrete outputs: conversion probabilities, money at risk, funnel stage outlook, Shapley attribution, and a CALL/NURTURE/VERIFY queue. It also distinguishes itself from the sibling lead_pipeline_get_engine by explicitly noting the size boundary for direct-row scoring.

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?

Provides explicit when-to-use guidance: pipelines ≤500 leads. It names the alternative (`lead_pipeline_get_engine`) for larger pipelines and explains why (slow, truncated JSON). It also states prerequisites (lead rows with lead_id and created_date), compatible data sources, and an explicit instruction not to invent scores when data is unavailable.

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