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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is not carrying that burden. It does add two useful behavioral facts not in structured data: results are ordered newest first, and legacy releases lacking typed changes are counted rather than guessed at – a real data-fidelity caveat that affects how an agent should interpret counts. It stops short of describing pagination or result caps.

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 tight sentences with zero filler; the resource and default window are front-loaded before the caveat. It is telegraphic to the point of minor ambiguity in places, but every clause earns its place.

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?

An output schema exists, so return values need no explanation, and the annotations plus schema cover the mechanical details. What is missing is disambiguation from the crowded set of change/release siblings – for a feed tool with fourteen neighbors, that omission leaves a real gap in calling it correctly rather than adequately.

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 three parameters (since, tools, include_deprecations) are already documented in the schema, including fuzzy tool-id resolution and the omit-for-all-tools rule. The description only restates the default 30-day window and the default-on deprecations behavior, adding no new semantics. 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?

The description names the concrete resource (breaking changes, including deprecations by default), the scope (across tools, time window), and the ordering (newest first). An agent can tell this is the breaking-changes feed rather than a general release feed. However, it never distinguishes this from close siblings like search_changes, whats_changed_since, or get_upgrade_notes, which is what holds it below 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 is implied by the tool's content type – an agent wanting breaking changes would reach for it – and the default window is stated. There is no explicit when-to-use, when-not-to-use, or named alternative such as search_changes for arbitrary change searching. Routing among the many sibling change-related tools is left entirely to inference.

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