Facebook

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

Beyond the read-only, open-world, and idempotent annotations, it discloses the credit cost of every resource, that failures are free, that max_age_days can return a cached copy for zero credits, and that list resources paginate via cursor. These are exactly the behavioral details an agent needs before invoking a metered call.

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 description is front-loaded with purpose and invocation rules, then a compact resource list. Given 18 resources and a metered dispatch model, it is dense but appropriately sized, with no filler.

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 complex dispatcher with no output schema, it covers routing, required arguments, costs, pagination, and caching, and it points to describe for additional parameter details. It could be more complete about output shape or about choosing between this tool and the narrower sibling getters, but the core call path is well specified.

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 basic meanings are already documented, but the description adds resource-specific semantics such as required url/id/query/location inputs and optional time, get_transcript, and allow_long_transcription. It also explains that resource-specific extras go in params and that describe supplies types and allowed values.

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 Facebook data and enumerates profiles, posts, videos, events, transcripts, comments, groups, locations, and products, while the resource list defines each operation. It is specific about what the tool does, but it does not explicitly distinguish the broad dispatcher from siblings such as get_profile, get_post, or get_comments.

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 explains the dispatch model: choose a resource, pass its parameters top-level, put extras in params, and reuse the cursor unchanged for pagination. It also points to describe for types and allowed values, but it does not state when to prefer this tool over the specialized sibling tools.

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