cors_simulate_fetch

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

No annotations are supplied, so the description carries the full burden. It does usefully disclose the observed behaviors it reports (origin_set_to_null, credentials_dropped, effective Max-Age), which signals a pure, side-effect-free simulation. It does not state that the tool performs no network I/O, that credentials mode changes mid-chain, or how the simulated stack decides hops, leaving some behavioral questions open.

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, front-loaded with the core action and followed by the reporting surface. Every clause carries information, though the parenthetical event list is slightly list-shaped rather than explanatory.

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 the description legitimately need not spell out return shapes, and it nonetheless sketches them. For a 9-parameter, nested-object tool with no annotations and a sibling that overlaps in intent, the description stops short of the routing and semantics detail an agent needs to call it correctly versus cors_evaluate.

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 78% with 9 parameters, so the schema does most of the documentation work. The description adds no parameter-level meaning at all: nothing explains how is_preflight interacts with redirects, or how mode/credentials shape the hop judgments. Baseline 3 is appropriate given the schema covers most fields, though the description could have clarified the semantically loaded ones.

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 gives a specific verb and resource: it walks a redirect chain hop by hop and judges each hop with the CORS check, and it enumerates the outputs (redirect events, visible headers, effective Access-Control-Max-Age). That is much clearer than a restated name. However, it never distinguishes itself from the sibling cors_evaluate, which an agent could easily mistake for this tool.

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?

There is no when-to-use guidance, no statement of prerequisites, and no mention of alternatives, even though cors_evaluate is a direct sibling that plausibly competes for the same intent. The agent must infer from the name alone that this tool is for multi-hop redirect scenarios while cors_evaluate covers a single exchange.

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