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

Beyond the annotations (readOnlyHint: false, destructiveHint: false), the description adds meaningful behavioral context. It explicitly states that calling it on an already-broken link is safe, implying it does not raise errors or cause side effects in such cases. The phrase 'without direct database access' clarifies the tool's abstraction level, which is not evident from the annotations alone.

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 concise, consisting of two sentences that convey the purpose, safety, and rationale. There is no redundant information or fluff. The structure is logical: first states the action, then clarifies its idempotent nature and the intended use case. Every word contributes to understanding the tool.

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?

Given the tool's simplicity (4 parameters, no output schema), the description covers the essential aspects: what it does, when it's safe, and why it exists. However, it does not specify the return value or behavior on success/failure (e.g., whether it returns a confirmation or error). This information might be inferred from similar tools but is not explicitly provided. Thus, it is nearly complete but lacks a small detail.

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?

The schema provides descriptions for all four parameters with 100% coverage, so the baseline is 3. The tool description does not add any additional meaning about the parameters themselves; it only refers to 'any supported pair,' which hints at constraints on entity types but does not elaborate on individual parameters. Since the schema already handles parameter details, this score reflects the lack of extra parameter semantics in the description.

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 tool's purpose: to unlink two entities of any supported pair. It uses a specific verb ('unlink') and identifies the resource ('entities'), and the title 'Unlink entities' reinforces this. The context of sibling tools, especially 'link_entities', makes the distinction obvious without needing to open 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?

The description provides explicit guidance on when to use this tool: it is safe to call even if the link is already broken or one side was deleted, making it idempotent. It also frames the tool as a primitive for clearing stuck link states, which helps the agent understand its role compared to other operations like 'link_entities' or database fixes. This is more than a generic statement and gives actionable context.

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