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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts beyond them: it makes no outbound network requests and retains no payload, and it identifies the equivalent REST endpoint. It still omits what the produced plan contains.

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?

Four short sentences, front-loaded with the core action, then mechanism, then the key behavioral guarantee, then endpoint equivalence. No filler and nothing that could be cut without losing information.

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 should explain the shape or meaning of the returned plan, and it does not — an agent cannot tell what a 'retrieval plan' item contains. Combined with 0% parameter coverage and nested objects, the definition leaves meaningful gaps despite a solid core statement.

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 and only partly meets it. It does map the three top-level inputs to plain language (resource manifest, cache validators, optional budgets), but nested fields such as etag, sha256, last_modified, max_items, accepted_types and max_total_bytes are never explained in either place.

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 and artifact ('Build a minimal conditional HTTP retrieval plan') and elaborates that it compares a caller-supplied manifest against cache validators and budgets. This clearly separates it from the sibling `fetch` by implication, though it never names `fetch` or any other sibling explicitly.

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 only implied: the plan/cache-validator framing and the note that no network requests are made suggest this is a pre-flight dry-run step, but there is no explicit 'use this when you want X instead of fetching' or stated prerequisites. The endpoint-equivalence sentence ('Same as POST ...') tells an agent the transport but not when to choose it.

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