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

Annotations only declare the generic non-idempotent/non-destructive write profile; the description adds real value by disclosing that every save creates a new revision rather than patching in place, that the entire document must be resupplied, and that activation happens by default unless activate is false. It does not say what happens to the previously active revision or what an invalid node list does, which is the main remaining gap.

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 write semantics and full-document requirement before the domain explanation; each sentence carries information. Slightly dense and mixes invocation guidance into the middle of the policy-model explanation, which makes it marginally harder to scan.

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 5-parameter, nested-object mutation with no output schema, the description covers the essential semantics: whole-document replacement, default activation, and the escalation-path structure that nodes must follow. What is missing is the response shape (e.g., whether the new revision id is returned) and whether the prior revision remains retrievable.

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 the schema already carries the bulk of parameter meaning. The description adds domain framing for nodes ('levels name current members as user targets, or broadcast') and the activate default, but repeat, working_hours and team_id get no additional explanation beyond the schema, so the baseline 3 holds.

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 ('Save a new revision'), a specific resource ('team's escalation policy'), and a crucial scope detail ('the whole document again, not a diff'), plus the default activation side effect. This distinguishes it from siblings like activate_team_escalation_policy_revision and update_escalation_path without requiring the schema.

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?

Gives a concrete prerequisite ('Call read_reference (escalation_paths) first') and explains the activate-flag behavior, which tells the agent how to control the outcome. However, it never contrasts itself with update_escalation_path, create_escalation_path, or activate_team_escalation_policy_revision, so sibling selection still requires inference.

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