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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the no-TAL/no-technician side effects, in-place replacement semantics for a repeated visit_layer_name vs. adding a second schedule, the UNDECLARED_FIELD failure mode, exclusion reporting (never silently dropped), and the post-submission sleep/poll/consume protocol. This is far beyond what a name and schema convey.

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?

It is long and dense, but front-loads the tier label, trigger condition, and core behavior before drilling into parameter nuance and workflow handoff. Most sentences carry unique information, though the volume approaches manual territory and a few constraints could be tightened.

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?

An output schema exists, so return values needn't be described, and the description still fills the remaining gaps: prerequisites, error behavior, ambiguity resolution against calculate_route, and the do_this_next follow-up. For a complex 18-parameter scheduler, an agent has everything needed to call it correctly.

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% with 18 parameters, so the description must compensate, and it does for the critical ones: it explains ts/ts_handle omission, frequency_unit semantics (interval_days vs. visits_per_horizon), never_visit_values defaults, visit_layer_name behavior, and max_buckets_per_day. However, roughly half the parameters (horizon, objective, map_session_id, schedule_label, guidance_handle, emit_visit_layer, expected_revision, cadence_flexibility_pct) receive no explanation.

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 uses a specific verb+resource framing ('Expands demand across a repeating horizon and packs it into daily work clusters'), and even states the core decision explicitly ('This tool decides the day'). It distinguishes itself from siblings by naming auto_build, cluster_points, and calculate_route, and by clarifying 'It creates no TAL and assigns no technician.'

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?

It gives an explicit trigger condition ('When: accounts carry a recurring cadence... and the user asks which day each visit happens'), names the neighbors, and even handles the ambiguity case ('When the user said route and a visit-frequency column exists, confirm they want a schedule, not calculate_route'). Prerequisites (ingest_accounts completed with cadence column declared) and follow-up routing are both stated.

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