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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the agent knows this is a non-idempotent write. The description adds the OAuth scope requirement, which the annotations do not cover. It does not, however, explain what happens on a duplicate assignment, which is the key behavioral question for a non-idempotent create.

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?

Two short sentences, zero waste: the action is front-loaded and the prerequisite follows. Nothing could be removed without losing information.

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 simple two-parameter join-table create with no output schema and annotations covering the safety profile, the definition covers what the agent needs to invoke it, including the scope prerequisite. The only gap is duplicate-assignment behavior, which is minor but relevant given idempotentHint=false.

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 100% with only two UUID parameters, both documented with format and pattern in the schema. The description adds no format, source, or constraint detail beyond the schema, so the baseline 3 is appropriate.

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?

States a specific verb and resource: 'Assign a contract to a site.' This clearly distinguishes it from create_contract (which creates the contract itself) and create_site. However, it does not differentiate from analogous join-table siblings such as create_service_area_site or create_project_site, which use the same assignment pattern.

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 supplies a required-privilege prerequisite ('Requires contract_sites:write scope'), which is useful context for invocation. But it gives no when-to-use guidance relative to alternatives like list_contract_sites or delete_contract_site, and no note about whether the contract/site must already exist.

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