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

Annotations already establish read-only, idempotent, non-destructive behavior, yet the description adds substantial context beyond them: Pro-tier gating, beta status, a concrete billing cost (10 read units per call), passage caps, and per-account daily quotas. It also discloses that passages are verbatim untrusted text and warns against following them as instructions, which is exactly the kind of safety-relevant trait annotations cannot express.

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?

Four tight sentences ordered by importance: capability, safety warning, language handling, then cost/limits. Nothing is repeated from the schema verbatim and no sentence is filler.

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 an output schema present, the description doesn't need to enumerate return fields, and it instead covers everything an agent needs to decide and call correctly: tier, cost, throughput caps, untrusted-content handling, and translation behavior. No material gap remains for this complexity level.

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 75% with one enum documented in the schema, but the description still adds meaning: 'up to 25 chosen bonds' reinforces maxItems, 'up to 10 passages per call' explains the limit ceiling, and 'words or a clause' frames how query and clause interact. It stops short of explaining the clause-plus-empty-query fallback, which lives only in the schema.

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 and resource (search the offering documents of chosen bonds) plus the scope constraint (up to 25 bonds) and the return shape (cited passages with document and page). This is clearly distinguishable from bondterminal_search_bonds, which searches for bonds rather than inside their documents.

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 'Pro only, beta' gate and quota limits tell an agent who may call it and how much they can call it, but there is no explicit when-to-use or when-not-to-use guidance versus siblings like search_bonds or get_terms. Usage is implied by the resource described rather than stated.

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