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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), and the description goes well beyond them: corpus size (tens of receipts), draft-withholding behavior with a separate count, and the crucial negative-result caveat. These are exactly the behavioral traits an agent needs to interpret an empty result correctly.

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?

Purpose and the negative-result caveat are front-loaded in the first two sentences, which is the right order. The trailing 'Args:' block duplicates schema descriptions that are already 100% covered, making it slightly longer than necessary.

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?

No output schema exists, so the description compensates by naming the returned fields and the human-openable URLs. Combined with the corpus-size and no-match caveats, an agent has everything needed to call it and to interpret both hit and miss results.

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 genuine semantics by stating what happens when neither filter is supplied (most recent published receipts) and clarifying that address matches subject or deployer containment. The rest largely restates schema text, keeping it below a 5.

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 (search) and resource (Scienter's published forensic receipts) plus the match modes (address or free text) and the return shape (titles, dates, subjects, public URLs). It is clearly distinguished from siblings like bridge_trace, cex_attribution or wallet_score, which are analytical rather than publication lookups.

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 real interpretive guidance: no match is normal and is not evidence of nothing happening, unverified drafts are withheld, and omitting both filters lists most recent receipts. It does not, however, route the agent toward or away from specific sibling tools, so it stops short of full when/when-not/alternatives guidance.

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