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

With no annotations present, the description carries the full burden and does so well: it discloses the immutable archive semantics, the meaning and finality of out_of_range, the transient/retry-after nature of pending, the unsupported-uid case, where limits live (get_meta), and points to ratehub://docs/behavior for remaining edge cases. An agent can reason about failure handling before the first call.

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 endpoint are front-loaded, and every sentence is substantive rather than filler. The status enumeration is crammed into dense run-on prose that would scan better as a list, and it partly restates the item 'status' field that the output schema already defines.

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?

For a three-required-array-param request against a rich output schema, the definition covers what the agent needs: scope, day constraints, per-item status semantics with retry policy, limit location, and a documented resource for deeper edge cases. Since an output schema exists, the description is not obliged to explain the response envelope further.

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% and the schema already documents assets as 'Catalog uids', vs as 'Quote currencies', and days as past UTC YYYY-MM-DD. The description restates the day format/UTC constraint but adds no extra parameter meaning (e.g. what a catalog uid is, how to obtain one, or per-call limits beyond a pointer to get_meta), so this sits at the 3 baseline for schema-documented params.

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 resource with clear qualifiers: immutable daily rates for catalog uids against quote currencies on UTC calendar days, plus the backing endpoint (POST /v1/rates/daily). The 'daily' granularity and 'immutable' property separate it from granularity-flexible siblings like get_rates and get_series without needing to open their schemas.

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 strong operational context: days must be past UTC dates, crypto history beyond ~a year comes from daily candles (source s8), and each status tells the caller whether to retry (pending), never retry (out_of_range), or treat the result as final (ok). It never explicitly contrasts this tool with siblings such as get_rates or get_series, so selection between them is left to inference.

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