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

With no annotations, the description fully carries the behavioral burden and does so richly: it discloses that workload omission still returns counts/metrics (workload_total null, never drive-only hours), that undeclared columns fail with UNDECLARED_FIELD, that metric cells are parsed leniently, that workload_total is in minutes while hours only come from grids, and that panel push duration is not proof the dock opened. This is far beyond what a schema could 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?

The guidance is valuable but delivered as a dense wall of text with repetition — workload omission is re-explained multiple times, dock behavior is revisited, and 'never invent a default (including 30 minutes)' restates an earlier point. Some length is justified by tool complexity, but it is not tightly front-loaded or easily scannable.

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?

Because an output schema exists, the description is not obligated to describe return values, and it still covers prerequisites, the failure mode (UNDECLARED_FIELD), units, and panel-state semantics comprehensively. The gap is the unexplained params, but for a tool of this complexity the behavioral coverage is nearly sufficient on its own.

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% across 15 parameters, so the description must compensate and it only partially does. It explains ts/ts_handle/job_id inputs, metrics semantics (omit for all declared columns, bare strings vs {field,label,type}), dwell_time, tal_ids in workload_omitted, and analysis_panel=single with map_session_id. Eight parameters (scope, max_depth, part_layer, compare_tals, guidance_handle, hypothetical_moves, visit_frequency_field) receive no explanation at all.

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 opens with a specific scope: '[Tier 1 — Analysis] When: balance diagnostics, cross-TAL comparison, or post-mutation facts,' which clearly identifies the resource and operation. It is distinct from analyze_routes by implication but never explicitly contrasts with sibling analysis tools. An agent understands what it does, though not the full boundary against nearby tools.

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 states explicit trigger conditions (balance diagnostics, cross-TAL comparison, post-mutation facts), prerequisites ('TAL exists; re-run after any TAL or point change (I-2)—never treat stale analysis as current'), and an alternative path ('Otherwise pass the full Analyze result ... to load_analysis_panel'). There is also an explicit prohibition: 'Do not ask for dwell before the first analyze just to avoid the note.'

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