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

The description directly contradicts the annotations: idempotentHint is false, yet the description claims 'Retry-safe: a repeat call with the same idempotency_key returns the original result,' which describes idempotent behavior. Although it adds valuable platform and empty-message behavior context, the contradiction with structured metadata is serious.

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 a single dense paragraph with the core action front-loaded. Every clause adds useful information about platform behavior, edge cases, return values, or retry semantics, though it is longer than a minimal definition.

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?

It covers behavior on supported versus unsupported platforms, the empty-message edge case, return values (sent status and provider message id), and retry safety. No output schema exists, and the description adequately explains what the caller receives. Minor gaps remain around several parameters.

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 50%. The description adds meaning beyond the schema by explaining that reply text goes in body.message and by describing idempotency_key semantics. It does not clarify query, brand_id, or workspace_id beyond what the schema already says.

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 ('Send a reply to the message, comment or review behind an inbox item') and names supported platforms. It distinguishes sending from drafting implicitly, but does not explicitly name sibling tools such as aidelly_generate_inbox_reply_draft.

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 explains when to use the tool (to reply to the message/comment/review behind an inbox item) and covers edge cases: unsupported platforms mark the item handled without sending, and an empty message sends nothing. It does not explicitly instruct when to draft first versus reply directly.

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