Link System Dependency

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

Annotation coverage is absent, so the description carries the burden of behavioral disclosure. It does disclose that the operation creates a compliance requirement with two independent satisfaction paths, and it documents the unlink behavior via passing an empty target_model_id. However, it does not mention whether the link is reversible in other ways, side effects on existing dependencies, permission requirements, or what the output looks like. The description adds meaningful context but leaves room for more behavioral detail.

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 reasonably concise and front-loaded with the main action, followed by explanatory details on effect, preconditions, unlink behavior, and related tools. The text would be 4-5 if not for the corrupted/truncated tail that appears in the raw description: after 'Inspect the resulting dependency graph with get_system_dependencies.' the description is followed by malformed fragments (e.g., 'TARGET MODEL ID + This description contains noise...'). Discounting that artifact, the meaningful part is efficient and well-organized, but the malformed content reduces clarity and demands a lower score.

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?

The tool has 4 parameters (3 required), a moderate parameter count, and an output schema exists which reduces the need to explain return values. The description covers the core action, preconditions, effect on the dependency graph, unlink option, and the two satisfaction paths, which together provide a solid operational picture. It does not describe server_version semantics or any error/validation behavior, and the malformed tail adds noise, but these are minor gaps given the presence of an output schema and the focused scope of the tool.

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 75%: the schema covers model_id, assumption_id, and target_model_id, but server_version has no description in the schema. The description adds important meaning beyond the schema by explaining the relationship between assumption_id and target_model_id ('external assumption', 'becomes cross-model dependency'), and clarifying the unlink semantics of an empty target_model_id, which is already hinted but reinforced. It also ties the parameter usage to a required precondition (assumption linked to control objectives). This compensates for the undocumented server_version parameter and adds value beyond 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 clearly states the action: linking an external assumption to a target model, and explains the effect: creating a cross-model system-scoped dependency and compliance requirement. It distinguishes this from local/current-model linkage by specifying 'in the same system' and 'cross-model (system-scoped)'. However, it does not explicitly contrast with other linking tools like add_assumption or submit_attestation, though it references them, so it stops short of full sibling differentiation.

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?

The description gives a clear precondition ('The assumption must already be linked to control objectives') and names related operations (add_assumption, edit_assumption, submit_attestation, get_system_dependencies) that indicate when to use this tool versus alternatives. It also explains two satisfaction pathways (auto-attestation and manual attestation) which help an agent understand the context. It does not explicitly state 'when NOT to use this tool' or list a direct alternative for the same action, but the context is strong enough for an agent to select it appropriately.

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