Get Deprecation Plan

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

Annotations already declare readOnlyHint=true; the description adds real behavioral detail beyond that: it returns null when nothing is deprecated, and includeUsage surfaces recent traffic and top consumers. This shapes caller expectations about both the null case and the optional enrichment. No contradiction with the read-only annotation.

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?

Three sentences, front-loaded with the core purpose; each sentence contributes purpose, null behavior, usage flag, and prerequisite. No filler, though the second sentence packs the usage guidance into a slightly dense parenthetical style.

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 compensates by naming the returned fields (phase, sunset date, successor, migration guide) and the null case. The entityType values are covered by the schema, and the readOnly annotation covers safety. It remains silent on project-context failure behavior, but nothing essential is missing for a read-only single-entity lookup.

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 all five parameters with descriptions and defaults. The description adds only marginal semantic value — framing includeUsage as a pre-retirement decision check — while usageDaysBack and the GUID fields are left entirely to the 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 states a specific verb and resource ('Get the deprecation plan of one endpoint or published version') with a clear scope, and itemizes the payload (phase, sunset date, successor, migration guide). It is clearly scoped to a single entity, which implicitly distinguishes it from list_deprecations, but it never names that or get_deprecation_policy as siblings.

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?

The description provides actionable context: 'Set includeUsage to also see whether anyone still calls it — do that before retiring' tells the agent when the flag matters, and 'Requires project context' states a necessary precondition. It does not, however, state when NOT to use this tool or name alternative tools for listing many deprecations.

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