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

With annotations only covering readOnly/idempotent/non-destructive, the description adds substantial behavioral context: deterministic keyword matching rather than LLM guessing, seat- and prerequisite-aware routing, up to 3 ranked paths, and exactly what each path carries (ordered steps, injected missing prerequisites, per-step auth, cost, outputs, failure hints, rulebook references). This is well beyond what the annotations provide.

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?

Front-loaded with the core purpose and examples before the return-shape detail, and every sentence carries information. The middle sentence is dense and slightly overloaded with a long list of path fields, but nothing is redundant.

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?

No output schema exists, so the description must carry the return contract — and it does, enumerating ranked paths, ordered steps, injected prerequisites, auth, cost, outputs, failure hints, and rulebook references. Combined with the state-flag guidance and the catalog alternative, an agent has everything needed to call and interpret this 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 coverage is 100%, so baseline is 3, but the description adds genuine meaning: it explains the shared purpose of has_account/has_user_key/has_sbt/has_bond_usd ('so the router doesn't re-suggest a step you've already done') and illustrates the free-text intent field, which the schema describes only as 'Free-text English description.'

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 precise verb+resource: 'Ask NightWatch's Agent Router which endpoints/MCP tools to call, in which order, for a plain-English intent.' The two concrete intent examples and the mention of the underlying endpoint (POST /agent/route) make it unmistakable against siblings like get_rules, tasks_browse, or agent_status.

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?

Gives concrete triggering examples and tells the agent to pass state flags so the router won't re-suggest completed steps, which is real usage guidance. It also names an alternative ('the whole catalog is also readable directly at GET /agent/catalog') for the browse-everything case. It lacks an explicit when-not-to-use or a comparison against sibling routing tools, so it stops short of 5.

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