graph_api_delete

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

With no annotations, the description carries the full burden of disclosing behavior, and it only conveys 'this mutates.' There is no mention that deletion is irreversible on Graph API edges, that Facebook credentials must be set (via set_facebook_credentials), what side effects or downstream resources are affected, or what errors/failure modes can occur. For a destructive, high-privilege operation this is a serious gap.

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 a single front-loaded sentence with no wasted words: it states the operation, the scope, and provides an embedded example. It is appropriately compact, though it leans so broad that its brevity edges toward under-specification, which is a completeness issue more than a conciseness flaw.

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?

Although an output schema exists, the definition lacks essential contextual detail: when the generic delete should be preferred over specialized siblings, how the edge string is formed for non-post entities, and what preconditions apply. Because it is a generalized, flexible deletion tool with a dangerous option, the missing operational context leaves an agent exposed to the wrong edge or unintended data loss, without escalation under covered.

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 0%, so the description must fill the gap. It does add meaning to the required 'edge' parameter by explaining it is a Graph API edge with a concrete example ('{post-id}'), which goes beyond the schema's bare 'Edge' label. However, the optional 'params' parameter is given no coverage in either the schema or description; an agent cannot reason about how, say, when params is a real JSON payload vs null, so the compensation is only partial.

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 is a single sentence with a specific verb ('DELETE') and a defined resource ('any Graph API edge'), and the example shows the shape of the edge value. It communicates that this is a generic catch-all deletion tool, which partially distinguishes it from targeted siblings like delete_post or delete_comment. However, it does not explicitly name those alternatives, so the differentiation from purpose-built destroyers is only implied, not stated.

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?

No guidance is given about when to use this generic delete versus delete_post or delete_comment, or whether this should be a last-resort fallback only. The example edge="{post-id}" hints at a common case but is not guidance about when to reach for the tool; there is no explicit use case, precondition, or why-this-one condition.

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