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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds substantial context beyond that: result ordering, the row grain, what each row contains, and that message text is untrusted third-party data that must be treated as data rather than instructions. It also discloses the auth requirement and how it can be satisfied.

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?

Five sentences, all front-loaded with the result shape first, then the filtering flag, then the follow-up tool, then the access requirement. The content is dense but every sentence carries information; the prompt-injection warning sits slightly awkwardly mid-paragraph but is warranted.

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?

There is no output schema, and the description compensates by describing the returned fields (handle, unread count, last message) and ordering. Combined with the auth note and the hand-off to the thread-reading sibling, an agent has everything needed to call and use this correctly.

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%, so the baseline is 3; the description still adds meaning by framing unread_only as 'conversations waiting for an answer' and by explaining where the profile_id/person_id values come from and where they are consumed. The limit parameter is left entirely to the schema, which is acceptable given its clarity.

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 ('most recent conversations in the sprkly inbox, newest first') and defines the row grain ('one row per person per connected account'), which is exactly the detail needed to tell it apart from the sibling sprkly_get_inbox_thread, which reads a single thread.

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 concrete routing guidance: pass unread_only for conversations waiting for an answer, and take profile_id and person_id from a row into sprkly_get_inbox_thread to read the thread. It also states the access precondition. There is no explicit when-not-to-use case, which keeps it just short of a 5.

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