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

Annotations already communicate mutation (readOnly=false), idempotency (idempotentHint=true), and non-destructiveness (destructive=false). The description adds a small behavioral clue, 'privacy-filtered project metadata', implying a constraint on the data to be sent. However, it does not describe behavior around conflicts, expectedVersion, or side effects, so it only slightly exceeds the annotation baseline.

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 sentence with no filler, front-loading the verb and resource. It earns its place by being concise, though this conciseness comes at the cost of essential detail. As a structure, it is clean and efficient.

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?

This tool has 7 parameters, a nested details object, 4 required parameters, no output schema, and minimal annotations. The one-sentence description is critically under-specified: it does not explain required fields, error conditions, the role of idempotencyKey, or how to construct details. An agent is not equipped to invoke this tool correctly without significant guesswork.

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 compensate for the absence of parameter semantics. It does not: no parameter is mentioned by name, and phrases like 'privacy-filtered project metadata' do not clarify the meaning of projectId, handoffId, idempotencyKey, expectedVersion, or the details object. The agent is left with only the schema's mechanical constraints.

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 includes a verb ('Update') and a resource ('hosted relay accept'), so it is not a tautology. However, 'hosted relay accept' is an undefined domain term, and with many relay_* siblings, it does not clearly differentiate itself (e.g., from relay_mark_sent or relay_release). An agent might struggle to know what 'accept' refers to.

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?

There is no guidance about when to use this tool versus alternatives like relay_dismiss or relay_release. No context, prerequisites, or conditions are stated. The description simply announces the action without explaining the workflow context.

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