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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the bar is lower — yet the description adds meaningful behavior beyond them: it is free, it reports which source produced each figure, it explicitly cannot prove causation, and it warns that a missing value is not zero and must be stated rather than invented. That is exactly the kind of epistemic and semantic caveat structured fields cannot carry.

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?

It is front-loaded with what the tool returns before moving to caveats, and each sentence carries distinct information (figures, safety, limitations, id semantics). It is slightly dense with emphasis ('THREE figures that must not be mixed up', 'CANNOT prove'), but that emphasis is load-bearing for a misuse-prone metric.

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 semantically tricky attribution tool with no output schema, the description names the three returned figures, their differing scopes, the source-provenance caveat and the missing-value rule, while annotations cover the safety profile. It does not describe the shape of the response payload, which with no output schema is the one remaining gap.

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 postId schema description is already rich, including that the figures are selected from the account's per-post totals. The description's contribution — that these are Soclo post ids, not platform ids — largely restates the schema, so baseline 3 is appropriate.

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 and resource — showing matched orders and link opens for one post — and immediately distinguishes its scope from the account-wide and shop-wide figures. An agent can tell this is the per-post attribution reader without opening the schema.

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 clear context for when to reach for it (per-post attribution) and scopes itself against the account-wide and shop-wide figures, and 'read-only and free' signals it is safe to call liberally. It stops short of naming the sibling tool that returns those broader figures (e.g. soclo_sales_overview), so the routing is implied rather than explicit.

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