list_project_policy_assignments

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

Annotations already carry readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful semantics beyond the annotations: the data is a decision-time snapshot ('while the outcome was unknown'), reinforcing the non-executing, non-learning nature of the operation. No contradiction with annotations.

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?

Two compact sentences with no wasted words: the first states action and scope, the second explains the data semantics and adds the safety-relevant exclusions. Every sentence earns its place and the key verb is front-loaded.

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?

For a simple 2-parameter read-only tool with strong annotations and an output schema present, the description adequately explains what the data represents. However, it lacks sibling-routing guidance among the many policy/learning-related tools (record_project_policy_assignment, list_project_policy_evaluations, evaluate_project_offline_policy) and does not clarify the limit parameter, leaving noticeable gaps.

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 0%, so the description carries the burden, but it only loosely hints at project_id semantics via 'for one project.' The limit parameter is entirely unaddressed beyond the schema default of 25, and no ID format or pagination semantics are provided. Description compensation is minimal for a 0%-coverage 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 uses a specific verb ('Read'), names a specific resource ('decision-time policy probability receipts'), and scopes it ('for one project'). The second sentence clarifies the otherwise jargon-heavy term by explaining the receipts show 'what alternatives and propensities existed while the outcome was unknown.' It doesn't explicitly differentiate from read-siblings like list_project_policy_evaluations, relying on generic negative statements instead, so it falls short of a 5.

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 context is implied: this is the tool for retrieving historical decision-time snapshots for a project. The negative clauses ('They do not execute actions or admit learning') hint at exclusions, but no sibling tool is named and no explicit conditions like 'use X instead when Y' are given. An agent can infer the use case but gets no positive routing guidance.

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