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

Annotations already declare non-destructive, non-read-only, open-world behavior, so the description's added context is what matters: it discloses that the call consumes no credits, that it also mutates status of already-saved posts, and that it returns the saved post including saved_key. It stops short of covering failure modes (e.g. invalid or expired job_id/post_key) or idempotency, which is why it is not a 5.

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?

Front-loaded with the core action and the input variants, then the routing rule, then the return value and cost. Dense and largely waste-free, though the first sentence is long enough that the three input modes would read better as a short list than as a comma-chained clause.

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 mutation tool with no output schema and no required parameters, the description covers source inputs, alternative tool, status semantics, return value (saved_key) and cost. Nothing an agent needs in order to call this correctly and interpret the result is missing.

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 baseline would be 3, but the description adds genuine meaning the schema does not: it establishes the mutual exclusivity of the input paths (job_id + post_key OR post_id OR saved_key) and frames saved_key as the status/note-change handle. That resolves the ambiguity created by six optional parameters with zero required fields.

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 verb and resource ('Saves a post to the creator's inspiration list') and enumerates the two input modes (viral search via job_id/post_key, tracked creator via post_id) plus the status-transition mode. An agent can distinguish it from save_to_library, list_inspiration and unsave_inspiration without opening any 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?

Gives an explicit when-to-use rule ('posts to come back to or remix later') and an explicit exclusion with the named alternative ('drafts and finished pieces go to save_to_library instead'). It also names the downstream tools the result feeds (get_transcript, generate_content), so the agent knows the follow-on path.

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