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

Beyond the annotations, the description explains real consequences: 'none' takes a link away, 'rejected' suppresses a term_graph proposal so it is not offered again, and 'confirmed' makes the link visible to readers and affects reading order. It also discloses that only project members who may write can use it, which is meaningful behavioral context for a destructive write operation.

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 the core operation and then adds relation-kind and state semantics in a compact paragraph. It is dense but largely earns its length, with only minor asides such as the issue reference that could be trimmed.

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 five-parameter destructive linking tool with no output schema, the description covers the crucial invocation details: relation kinds, state effects, term naming, the 'to' scope constraint, and write permissions. An agent has enough information to call it correctly without needing return-value details.

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 already documents all five parameters at full coverage, but the description adds substantial semantic detail for 'kind' and 'state', including defaults and downstream effects. It also adds the constraint that 'to' must belong to the project or one above it, which is not obvious from the schema alone.

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 states a specific operation: linking one project term to another with a relation kind. It clearly distinguishes the three relation kinds and covers link state changes, but it does not explicitly differentiate this tool from siblings such as define_term, merge_terms, or term_graph.

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 clear usage context for 'state' values: 'confirmed' keeps the link, 'rejected' declines a proposed link, and 'none' removes a link. It also states the permission requirement and the constraint on 'to', though it does not name alternative tools or explicitly say when to prefer this over them.

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