grapple_initiate

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

With no annotations, the description carries full burden and delivers. It discloses that missing prerequisite facts return 'cannot-adjudicate', explains the conditional presence of the dc field depending on str_modifier and proficiency_bonus, and clarifies that formula blanks may be omitted. It also explicitly scopes out the save resolution and escape contest, giving a complete behavioral model.

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 three sentences: purpose, prerequisites/error behavior, and return/scope. Every sentence carries substantive information with no filler, and the structure front-loads the main purpose then details constraints and output behavior.

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 complexity (11 params, nested objects), the description is fairly complete for the domain logic: it covers the SRD reference, prerequisite checks, conditional DC output, and the separation from save.check. It does not explain the policy/table parameters, but these may be system-wide conventions; the core adjudication behavior is well-specified.

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 low (27%), and the description partially compensates. It clarifies that attacker_size and target_size are both required, that has_free_hand is needed for grapple, and how str_modifier and proficiency_bonus affect the output's dc field. However, the numerous policy-related parameters (table_policy, asserted_facts, policy_context, table_decision) are not explained in the description, leaving a significant gap.

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 verb+resource: 'Adjudicate initiating a Grapple or Shove via an Unarmed Strike' and cites the exact source (SRD 5.2.1 p.190). It clearly distinguishes this tool from sibling save/check tools by stating the target's save is resolved separately via save.check and the escape contest is out of scope.

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?

The description gives clear context for use: it adjudicates the initiation step and explicitly delegates the target's save to save.check, defining what is out of scope (escape contest). It also states required inputs ('Both sizes are required; Grapple also requires has_free_hand'), helping callers know when they can call the tool. It does not explicitly name alternatives, but the scope exclusions provide practical guidance.

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