Facebook: Page

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

Annotations only declare the read-only/non-destructive/open-world safety profile, and the description adds a great deal beyond that: per-action credit pricing (including the 5-credit surcharge for exact_followers_count and ceil(posts_returned/3) for posts), per-action return volumes (3-9 posts, 6-12 videos, 8-16 albums), and pagination via end_cursor. The deeper-scrape behavior behind exact_followers_count ('38,493,217 instead of "38M"') is disclosed before the agent spends the credits.

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 summary sentence followed by one consistently formatted block per action, which is the right structure for a 7-action tool. It is dense with no filler, though the repeated 'Pricing: N credit per call' lines and a few Inputs lines restate what the schema already lists, adding mild redundancy.

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 10-parameter, 7-action tool with an output schema, this definition covers everything an agent needs to choose an action, satisfy its parameter requirements, chain calls (id -> albums -> album_items), and anticipate cost and pagination. Return values are described as a bonus even though the output schema already carries them.

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 description coverage is already 100%, so the baseline is 3, but the description adds workflow semantics the schema cannot express: which parameters each action needs, that profile_id is the numeric ID obtained from action=id, that album_id must come from action=albums or facebook_group, and that link/profile_id are interchangeable for videos. It also explains the effect of after_time/before_time and timezone on the posts action.

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 opening sentence names the resource (Facebook pages) and the data surface (profile details, page ID, posts, videos, reels, photo albums), then enumerates all seven actions with a specific verb+object for each. Sibling boundaries are made explicit: facebook_search (action=pages) to find a page by name, facebook_group (action=albums) as another album_id source, and action=videos vs action=reels vs action=posts.

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?

Every action carries a when-to-use clause plus a named alternative: 'use it when you have the page URL; to find a page by name, use facebook_search (action=pages) first', 'use action=details for the page's data', 'For reels or videos only, use action=reels or action=videos', 'For long-form videos, use action=videos'. Cross-action dependencies (album_id comes from action=albums, profile_id from action=id) are spelled out rather than left to inference.

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