conditional_evaluate

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

With no annotations, the description carries the full burden and does well: it discloses the precedence order applied, the short-circuit behavior ('stopping at the first applicable one'), and the discrete outcome set (200|304|412) plus the deciding rule and clause references. It stops short of stating that evaluation is side-effect free and does not touch the resource.

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?

A single dense sentence that front-loads the action and then the algorithm and outputs in descending priority. Every clause carries information, though the comma-chained precedence/return list is slightly heavy to parse; a second short sentence would have been cleaner without adding length.

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 nested-schema tool with an output schema (so return values need not be explained) and no annotations, the description supplies the algorithm, precedence rule, and outcome set an agent needs. It lacks only the sibling-disambiguation and side-effect/purity statement, which are modest gaps given how self-contained the tool is.

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 coverage is 67%, so the schema documents most of method, resource.etag, resource.last_modified, and request_headers. The description indirectly signals which header names in request_headers are meaningful (the four conditional headers), which is some added semantic value, but it explains nothing about how method or resource interact with those headers.

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?

Names a specific verb+resource: judging one request's precondition headers and reporting the resulting status. The scope (If-Match, If-Unmodified-Since, If-None-Match, If-Modified-Since) clearly separates it from siblings like cache_evaluate, cors_evaluate, and vary_match; an agent can route without opening 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?

The RFC 9110 §13.2.2 framing implies the context (HTTP conditional request evaluation), so usage is inferable. However, it never states when to prefer this over cache_evaluate or vary_match, nor any when-not condition or prerequisite (e.g. that resource state must be supplied). No explicit routing guidance.

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