Extract citable chunks

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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so this is a safe read/idempotent operation. The description adds a valuable behavioral note: the output includes a 'transparent heuristic score' explaining why each chunk was selected, which goes beyond what a simple 'extract chunks' tool would imply. This transparency about the scoring mechanism is genuinely useful context not present in annotations.

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, efficient sentence that conveys the core purpose and the key output behavior (transparent heuristic scores). Zero wasted words, front-loaded with the action verb. No filler or redundancy.

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, idempotent extraction tool with only 2 parameters and no output schema or nested objects, the description covers the essential behavior: what it extracts and that it provides transparent scoring. The main gap is the undocumented limit parameter's semantics, but given the tool's simplicity and strong annotation coverage (safe, read-only, idempotent), the description is reasonably complete.

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 50%: the url parameter has a description ('Public webpage URL') but limit has only a default value with no description text. The description adds minimal parameter meaning—no mention of what limit controls (number of chunks returned) or how it interacts with the scoring threshold. Baseline 3 applies given partial coverage, but the description doesn't compensate for the undocumented limit parameter.

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 uses a specific verb ('Find') and resource ('concise standalone definitions and factual passages on a page'), clearly stating what the tool extracts. It doesn't explicitly differentiate from siblings, but the AEO sibling family is large; while the 'citable chunks' concept is fairly unique among them, the description doesn't name an alternative. Still clear enough for primary purpose.

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?

No explicit when-to-use or when-not-to-use guidance is given. The description mentions it explains a 'transparent heuristic score' which hints at its distinguishing feature, but it never tells the user when to prefer this over similar AEO tools like aeo_citation_readiness or aeo_ai_readability_audit. Context must be inferred entirely from the tool name and description.

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