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

Annotations already cover read-only and idempotency, but the description adds substantial context beyond them: cache-served with no billing, never rebuilds, and a payload warning that include_physical can reach hundreds of KB for a dense page. That cost/size disclosure is the kind of thing annotations cannot express. It stops short of describing output structure or failure modes, which is acceptable given an output schema exists.

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 what it returns, then when to call it, then how to call it. No filler; the payload-size caveat is placed exactly where the agent makes the include_physical decision.

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 read-only drill-down with an output schema, all deciding information is present: prerequisite tool, selection criteria, key parameter provenance, and the one optional parameter's cost tradeoff. Nothing needed to invoke it correctly is missing.

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 100%, so the baseline is 3; the description adds real guidance the schema does not, namely that documentRef should be the document.sha256 from a prior map result and that it is served free from cache. It also reinforces include_physical's weight, though some of that duplicates the schema's own 'Heavy — default false' note.

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 resource ('Tier-2 detail for ONE page of an already-mapped datasheet') and enumerates what is returned: measured anatomy, headings/first lines, and claiming modules. It explicitly positions itself relative to datasheetvend_extract_document_map, so an agent can separate the two without opening a 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?

Gives an explicit sequencing rule ('Use it AFTER datasheetvend_extract_document_map') plus the triggering condition ('when the Tier-1 index says a page matters and its one-line summary is not enough'). It also names the one real decision point, include_physical, and gates it with 'ONLY when you truly need'.

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