Read the latest streamed prices

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

With no annotations, the description carries the behavioral burden and does well: it discloses cache semantics, immediate return, zero rate-limit cost, and the meaning of stale ageMs. It does not cover error cases or what happens if no subscriptions exist, but the disclosed behavior is materially useful and non-obvious.

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?

Two focused sentences with no filler. The core purpose is front-loaded, and the caveat about ageMs is a necessary, well-placed warning rather than extraneous detail.

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?

The description is complete for a low-complexity one-parameter cache lookup, but there is no output schema and the description only names ageMs as a row field. It leaves the exact tick/price field names to inference, which is a meaningful gap for an agent needing to present a price.

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%, so the optional scripCodes parameter is already fully documented. The description adds context about streamed instruments and ageMs but does not need to repeat the schema's parameter semantics.

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 states a specific verb ('Read') and resource ('streamed instrument'), and clarifies it is a cache lookup rather than a network call. This clearly distinguishes it from siblings like get_quotes and watch_prices without ambiguity.

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 gives clear context: this returns the most recent cached tick instantly and costs no rate limit, implying it is for quick cache reads rather than live fetches. It also advises checking ageMs before presenting prices, which is practical usage guidance, but it does not explicitly name alternatives or exclusions.

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