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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds that this is a non-mutating policy gate applied prior to reproduction, which is useful context. It does not disclose what drives the verdict — precedence among license text, site profile, and source signals — or what 'blocked' means operationally, so it adds only modest value beyond the 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 sentence with no filler, and the key outcome vocabulary is front-loaded in the position an agent reads first. It is arguably too compressed rather than too long — the terseness borders on cryptic for a five-parameter decision tool — but there is no wasted wording to cut.

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 return values need no explanation, and the schema covers all inputs, which lowers the burden considerably. However, for a decision tool whose correctness depends on the interaction between license_text, site_profile, and source_signals, the description leaves the decision logic entirely opaque and never routes the agent to or away from plan_reproduction_path. Adequate, with a clear gap.

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 100% and every one of the five parameters carries a substantive description, including cross-references to discover_embed_candidates and inspect_url. The description itself contributes no parameter meaning at all — nothing about how license_text overrides signals or how exact_requested shifts the outcome. Baseline 3 applies when the schema does all the work.

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 ('Decide') and a concrete resource ('a reference') and enumerates the exact outcome classes: embedded, sourced, locally captured, bounded-rebuilt, blocked. That is far more than a restatement of the name. It stops short of distinguishing itself from the closest sibling, plan_reproduction_path, so it is not a 5.

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 trailing phrase 'before reproduction' implies sequencing — call this ahead of planning/generation — which is real, if implicit, guidance. There is no explicit statement of when-not to use it, no prerequisites (e.g. that candidates must first come from discover_embed_candidates), and no named alternative sibling. Usage is inferable but not spelled out.

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