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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the description need not re-explain safety. It contributes real behavioral context beyond them: the prerequisite that media must be uploaded first, the two-URN dependency chain (get_me → author_urn, list_managed_pages → page_id), and the concrete shape of the returned URN. It is silent on idempotency behavior and on what happens to an orphaned multi-photo object if create_post is never called, which keeps it from 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?

Four sentences, front-loaded with purpose, then the return value, then account selection, then usage conditions — a sensible order with no filler. It loses a point for mild redundancy: the create_post handoff is stated twice ('to pass to create_post' and 'returns the single URN create_post takes').

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 create/mutation tool with an output schema available, the description covers everything decision-critical: prerequisites, the two identity modes, the downstream consumer of the returned URN, and when not to use it. Return-value detail and idempotency semantics are fully carried by the output schema and the idempotency_key parameter description respectively, so nothing an agent needs 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 the baseline is 3, but the description adds relational meaning the schema only implies: author_urn is the account identity obtained from get_me and is replaced (not supplemented) by page_id for page posts. The 'two or more images' constraint on media_urns is also only in the prose. alt_texts and idempotency_key are left entirely to 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?

The description opens with a specific verb and resource ('Create a LinkedIn multi-photo object from a list of digitalmediaAsset URNs') and immediately states the output artifact ('Returns an identifierUrn (urn:li:fsd_multiPhoto:…)'). It also carves out its scope against siblings by naming create_post, upload_media_from_url and get_me, so an agent can place it in the pipeline 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 an explicit ordering prerequisite ('Use after uploading two or more images with upload_media_from_url'), a downstream handoff ('returns the single URN create_post takes'), and a stated exclusion ('Not for one image'). It also routes the agent on the company-page branch ('for a company page post pass page_id instead'), which is the main branching decision an agent faces here.

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