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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely non-obvious context beyond that: the response is derived from stored data with no advertising API calls (implying freshness/latency characteristics), and it pre-empts a likely misinterpretation by explaining that refused_before_delivery.consent counts consent_basis=severed_measurement rather than banner refusals, with other opt-outs falling under reason_unknown.

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-loaded with the purpose sentence, followed by a scoping constraint and then field-level semantic caveats that are dense but each carry real interpretive value. Four sentences with no filler, though the caveat block is jargon-heavy and would benefit from being visually separated from the purpose statement.

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 must carry return-value semantics, and it does reasonably well by enumerating the four reported dimensions and decoding the trickiest nested field plus the 0-1 scale of consent rates. It still does not convey the overall response structure (how delivery outcomes, gaps, identity presence, and journey coverage are organized), leaving a modest gap for a report-style 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?

Schema description coverage is 100%, so all four parameters (to, from, workspace_id, conversion_kinds) are already documented with defaults and formats. The description only indirectly touches workspace scoping via 'authorized workspace' and adds nothing about the time window or conversion kind filtering. Baseline 3 applies when the schema does the heavy lifting.

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 (read) and a well-defined resource set: conversion delivery outcomes, delivery gaps, retained identity presence, and journey coverage, scoped to an authorized workspace. An agent can tell it is a read-only diagnostics report rather than an action tool, though it never explicitly distinguishes itself from close siblings like get_signal_health, get_consent_rates, or get_conversion_journeys, which cover overlapping ground.

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 the scope statement ('for an authorized workspace', 'uses stored data only'), which tells the agent this is a historical/stored-data diagnostic rather than a live ad-platform query. However, there is no explicit when-to-use, when-not-to-use, or routing to the several sibling tools that report overlapping signal metrics.

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