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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuine behavioral context beyond that: results are ordered oldest-first, the change entry only carries the latest call's arguments, and the return dict exposes `has_more` for pagination.

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 summary is front-loaded and the XML-tagged returns block is compact. Content is efficient, though the tag scaffolding is slightly heavier than plain prose would require.

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 usefully compensates by documenting the return dict (calls with id/created_at/arguments, has_more) and the pagination loop. For a read-only, well-annotated tool this is essentially complete, with only auth/permission context absent.

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 documents limit, offset, agent_id and change_id. The description reinforces the offset pagination intent ('oldest first', `has_more`), but adds no syntax or format details beyond the schema, making the baseline 3 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 summary states a specific verb (read) and resource (every call in one change made by MCP clients), plus the scope constraint 'oldest first.' It distinguishes itself from any sibling that surfaces change entries by clarifying it returns the individual calls rather than only the latest one.

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?

It gives a concrete when-to-use condition: 'use this when you need the others' (beyond the latest call's arguments), with a worked example of an `update_prospect` burst. It doesn't state any when-not or name an alternative tool to prefer, so it falls short of a full 5.

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