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

Annotations carry only readOnlyHint=false, so the description does the heavy lifting: it discloses that a counterargument is auto-written before any ruling, that a fresh Magistrate rules, that a missing Magistrate yields DEEP_REVIEW_PENDING with no ruling, and the one-referral-per-copy limit. These are real behavioral traits beyond anything 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-loads the crucial scoping ('Practice mode, Consumer Pulse copy only') and remains a tight cluster of sentences with little waste despite dense content. Slightly long and packed, but each clause adds actionable information.

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?

For a mutation tool with no output schema and minimal annotations, it covers the lifecycle (referral, counterargument, ruling), the failure mode (DEEP_REVIEW_PENDING), and the constraints (one side, one referral per copy). Only the success-path post-ruling outcome is left somewhat implicit.

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 50%, so compensation is needed. The description supplies semantic meaning for the 'side' enum ('forecast' = model's +2.1%, 'panel_b' = Panel B's +0.4%) and the reasons limit (up to 1,000 characters), while matter_id and actor_token are already documented in the schema.

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 specific verb (refer) and resource (the Q4 conflict to a Magistrate), plus the exact scope: argue ONE side. It explicitly contrasts with atlas.pulse_ruling, which only reports the DEEP_REVIEW_PENDING state, so an agent can tell the two apart without opening either schema.

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?

Scopes usage tightly ('Practice mode, Consumer Pulse copy only (Magistrate demo, step 3)') and gives hard constraints: cannot supply a ruling, cannot file both sides, one referral per copy. It points to atlas.pulse_ruling for the no-Magistrate case, but does not explicitly say when to prefer a ruling/referral path or name a sibling alternative for the act of arguing.

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