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

The description claims the tool is 'read-only' and says 'anything that buys, sells or writes refuses', but annotations set readOnlyHint=false. This is a direct contradiction. The extra 'seat on The Wall' and 'Rokha's sandbox' phrasing adds jargon rather than behavioral clarity.

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 first clause is useful, but the description quickly becomes a run-on with an incomplete phrase ('plus the agent-declared —'), unexplained sandbox/seat jargon, and a registry URL. It is not economically concise and is poorly structured for an agent to parse quickly.

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 tool with four required nested parameters and no output schema, the description is severely incomplete. It does not explain what the sidecar contains, how the inputs map to the output, or what the agent should expect after calling the tool.

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% and the description names none of the four required parameters (manifestDigest, project, dimensions, capabilities). With highly nested required inputs and no compensating explanation, the description leaves parameter semantics entirely to the schema.

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 opens with a concrete verb and resource: 'Build a canonical, read-only aas-selection-evidence.json sidecar' from the session's search/get/compose/inspect trace. It is clear about the core purpose, but it does not explicitly differentiate from siblings like inspect_selection_evidence or compose_stack, and the sentence becomes garbled with 'agent-declared —' and 'seat on The Wall' context.

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 when-to-use guidance or mention of alternatives. The only behavioral note is 'Read-shaped tools only', which is a constraint rather than a usage guideline. An agent is not told when to choose export_selection_evidence over inspect_selection_evidence or compose_stack.

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