get_context_brief

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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds two real behavioral facts beyond them — output is bounded and carries provenance — but never explains what the bound is, how fresh the data is, or what provenance looks like. Useful added context, well short of full disclosure.

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?

A single front-loaded sentence with zero filler: verb, resource, distinguishing property, and contrast all in under a dozen words. Nothing repeats the name or the annotations, and nothing could be cut without losing meaning.

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?

With no parameters, no output schema, and annotations covering the safety and openness profile, the description carries only the burden of explaining what comes back — and it does so vaguely. "Bounded" and "provenance" are the right concepts but are undefined, so an agent knows the shape of the answer without knowing its contents or limits.

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?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The one thing an agent might want — whether the briefing can be scoped or filtered — is implicitly answered by "bounded" and the empty schema together.

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?

"Read a bounded context briefing with provenance" names a specific verb and resource, and the trailing clause explicitly contrasts it with a different thing (an inferred user profile). However, "context briefing" is left abstract — the agent must guess what the briefing actually contains, and no sibling (get_facts, get_evidence_bundle, search_memory) is named, so sibling differentiation is conceptual rather than explicit.

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 "not an inferred user profile" implies when this tool is appropriate (when sourced, bounded context is wanted rather than interpretation), but there is no explicit when-to-use/when-not against the six sibling retrieval tools. The agent can infer intent but receives no routing rule for choosing between this and get_facts or get_evidence_bundle.

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