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

Annotations already provide read-only, idempotent, and non-destructive hints, but the description adds valuable specifics: it 'does not call Grok, does not invent evidence, does not mutate Substack or Azure Blob, and does not treat TripCodes as official SEC identities.' It also explains behavior like resolving TF-SUB objects and marking missing evidence explicitly, which goes well 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?

The description is a single dense paragraph but front-loads the most important usage information. It is broken into logical sections ('Parameters:', 'Behavior:') inside the prose, and every sentence adds value without unnecessary fluff. Slightly verbose but still efficient.

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?

Given 25 optional parameters, no required fields, an output schema, and a complex synthesis workflow, the description covers the key trigger, parameter usage, HUT special case, behavior guarantees, and return sections. It could mention failure modes when Azure Blob is not configured, but it does specify the conditional ('when Azure Blob is configured'), so it is fairly 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 coverage is 100%, so baseline is 3. The description adds meaningful guidance by naming key parameters (article_tripcode, tripcode, prior_article_tripcodes, linked_xbrl_tripcodes, filing_tripcodes, ticker) and explaining the HUT fallback when filing_tripcodes is omitted. This clarifies parameter relationships beyond what the schema descriptions provide.

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 clearly states the tool's purpose: 'Use this read-only synthesis tool when a subscriber gives Codex or Claude Code a DeltaSignal article TripCode and asks for the thesis map behind the article.' It names a specific verb ('synthesis'), resource ('thesis map'), and trigger context, distinguishing it from sibling tools like compare_claim_to_evidence.

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 description provides explicit usage context: when a subscriber requests a thesis map with an article TripCode. It also clarifies parameter preferences ('pass article_tripcode or tripcode') and the HUT fallback with the seeded filing pack. However, it does not explicitly name alternative tools or say when not to use it, so a small deduction.

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