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

There are no annotations, so the description carries the full behavioral burden. It discloses that only approved Signals can be explained, unapproved ids return not found, daily read limits exist, repeated reads of the same product are free, abuse can be refused/scored/suspended, every response has a status, statuses describe the Record rather than product truth, and observation dates/windows are not exact change dates. That is unusually complete behavioral disclosure.

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 long, but it is organized with clear sections ('When to use', 'What it cannot provide', 'Limits') and is front-loaded with the core definition. Nearly every sentence contributes operational or interpretive value, and the length is justified by the absence of annotations and the number of important caveats an agent must respect.

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?

With no output schema, the description compensates by explaining what responses contain (status, limitations, before/after, observation window, evidence), what statuses mean, and how to interpret them. It also covers access limits, misuse consequences, coverage limitations, and temporal semantics, making it complete for an agent to decide when and how to call the tool.

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?

The schema already documents signal_id as a canonical id, not a display name, at 100% coverage. The description adds meaningful context: the id must correspond to an approved Signal, and an unapproved id returns not found. It does not give an id format or example, but for a single fully documented parameter the added semantics are sufficient.

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 opens with a specific verb and resource: 'Explain one approved FormulaSignal Signal' and defines it as a confirmed, reviewed change between two comparable product states. It also states what the explanation covers (before state, after state, observation window, evidence), which distinguishes it from sibling list/compare/search tools even though no sibling is named.

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?

It gives an explicit 'When to use' condition: when a product record or history response named a signal_id and the agent needs before/after state, observation window, and evidence. It also provides exclusions: no unreviewed candidates, review deliberation, or internal queue access, and a warning not to iterate to reconstruct a Record. However, it does not name a specific alternative sibling tool for those excluded cases, so it stops short of a full 5.

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