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

Annotations only say readOnly=false, destructive=false, openWorld=false; the description adds the behavioral facts that matter: the link lives 2 hours, is bound to this profile only, requires no sign-in from the recipient, lands on a draft or the Library, and nothing is published. It also discloses a real constraint (Grok Bot only passes files up to ~10 MB) and prescribes how to phrase that to the user, which is exactly the kind of context annotations 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?

The core constraint is front-loaded in the first clause, and almost every sentence carries an actionable rule. It is dense though — long colon/semicolon-chained sentences mix operational routing, user-facing phrasing guidance ('never "inaccessible"'), and link formatting instructions, which an agent must parse apart rather than skim.

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 one-parameter tool with an output schema, this covers everything an agent needs: when to call it, what must precede it, where the file lands, how long the link lasts, how to present it, and what to call afterward. Nothing material is left to inference.

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 single parameter is already documented, so the schema does most of the work. The description still adds meaning beyond it: post_id routes the file onto that specific draft automatically, omitting it sends the file to the Library, and the draft must exist first via postkey_create_post. That sequencing implication is not derivable from the schema.

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 artifact ('Makes a link') plus the resource it requests (a file), and immediately scopes it against the sibling that would otherwise be chosen: 'you tried postkey_begin_upload and cannot read the file or run a command.' An agent can distinguish this from postkey_begin_upload, postkey_attach_library_item and postkey_create_post 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 positive trigger (file unreadable or still only on their phone), an explicit negative (never ask for what they already sent; chat attachments go through postkey_begin_upload first), and follow-up routing (postkey_get_post or postkey_list_library once the person confirms). The prerequisite 'call postkey_create_post first so the post exists' is a concrete ordering rule most definitions omit.

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