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

Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds that the output is canonical, that inputs come from the session trace plus the agent-declared capability ledger, and that validation is structure/integrity-only with no semantic judgment. This meaningfully extends the annotations and does not contradict them.

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 dense sentences with no filler. The first front-loads the action, output artifact, and input source; the second adds the key validation boundary. Every phrase 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 input schema is large and nested with no textual parameter descriptions, and there is no output schema, so the description should bridge those gaps. It communicates the tool's high-level purpose and limitation well, but does not explain what manifestDigest represents, how the parameters relate to the trace/ledger, or what the tool returns. Adequate, but with clear gaps for a complex 4-parameter 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%, so the description must compensate, but it only loosely maps the 'agent-declared capability ledger' to the capabilities parameter. It says nothing meaningful about manifestDigest, project, or dimensions, and does not explain how the session trace maps to parameters. The schema's names and constraints hint at meaning, but the description provides minimal added guidance.

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 action ('Build') and resource ('canonical, read-only aas-selection-evidence.json sidecar'), and identifies the source: the session's actual search, get, compose, and inspect trace plus the capability ledger. This clearly differentiates it from sibling tools like inspect_selection_evidence or compose_stack, which inspect or compose rather than export a sidecar.

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?

Provides clear context: this is the structural export step for a session's evidence, and it explicitly says the tool does not judge semantic fit or coverage quality, signaling when NOT to rely on it. It does not name an alternative tool or give an explicit when-not-to-use scenario, so it stops short of full routing guidance.

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