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

Annotations indicate readOnlyHint=false and destructiveHint=false, so the description adds value by clarifying the tool never submits a transaction yet still advances the workflow. It also discloses the auth requirement (session capability token). This goes beyond what annotations alone convey.

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 sentences with no filler. The core purpose is front-loaded, and the critical constraints (token requirement, no transaction submission) are stated immediately. Every sentence earns its place.

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 description covers purpose, auth, and the no-submission constraint, but with no output schema and no return-value description, it leaves the agent uncertain about the result or next workflow step. It also omits idempotency semantics despite an idempotency_key parameter. This is adequate but not fully complete.

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, but it only indirectly maps to session_token ('session capability token') and transaction_hashes ('source transaction hashes'). It does not explain session_id or idempotency_key, leaving significant semantic gaps for an agent invoking this tool.

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 identifies the action (observe), the resource (caller's already-submitted source transaction hashes), and the scope (v2 session). It distinguishes from sibling observe_output by explicitly mentioning 'source' transaction hashes, though 'advance the workflow' is somewhat vague.

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 phrase 'already-submitted source transaction hashes' implies the tool should be used after the caller has submitted transactions, and 'Never submits a transaction' clarifies it is not for submission. It provides clear context but does not explicitly name alternative tools or when-not-to-use conditions.

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