sovereign_route_and_analyze

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'NanoRunner synthesis' and 'execution_mode telemetry' but does not explain what side effects, permissions, or performance characteristics exist. It does not state whether this tool is read-only or has implications for data retrieval, error handling, or security beyond the user_clearance parameter. The description is vague about what happens when a query is routed, whether synthesis is optional, or if any state changes occur.

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, dense sentence stuffed with jargon and internal references (ADR-40, NanoRunner, MAC pushdown) that are meaningless to an agent without prior context. It lacks front-loading of the tool's core purpose; the keyword 'Routes' appears mid-sentence. Conciseness is sacrificed for technical flair, making it hard 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?

Given the tool's complexity (routing, multiple retrieval types, synthesis, telemetry), the description is inadequate. It does not explain the two-pronged routing logic in practical terms, when to set synthesize=false, or how user_clearance affects results. With no output schema, the description should clarify what the agent can expect in return, but it only mentions 'fast_summary with execution_mode telemetry' without details. The external context signals (siblings) are not leveraged, so the description is incomplete for correct invocation.

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 100%, so the schema already documents all four parameters (query, limit, synthesize, user_clearance) with descriptions. The tool description adds some context by mentioning 'explicit execution_mode telemetry' and 'NanoRunner synthesis', which hints at the synthesize parameter's purpose. However, it does not elaborate on query types beyond listing them, and the user_clearance parameter's role in 'MAC pushdown' is only mentioned in passing. The description adds minimal value beyond the schema, so baseline 3 is appropriate.

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 states a specific verb and resource ('Executes... Retrieval & Resilient Intent Router'), but uses jargon ('Two-Pronged Hybrid Retrieval', 'MAC pushdown', 'multi-tier cognitive queries') that obscures what the tool actually does. It distinguishes itself from siblings only by naming internal components, not by describing its practical function. An agent could infer it routes and analyzes queries, but the description is dense and not immediately clear.

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 explicit guidance on when to use this tool versus siblings like sovereign_search_vault or sovereign_get_entity_dossier. The description mentions routing deterministic identifiers vs cognitive queries but doesn't tell the agent which type of query should be directed here versus a sibling. The tool's role in the overall workflow is implied but not stated, leaving the agent to guess.

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