add-free-cast

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

With no annotations provided, the description carries the full disclosure burden and excels: it details all permanent effects (spell becomes ALWAYS-PREPARED, cast activity lands on the granting feature, Additional Spells entry is created), the MIGRATION of the old shape off the spell, deduping of cached copies, and idempotency. The explicit 'NEVER' warning further clarifies what the tool will not do, leaving no behavioral surprises for the agent.

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 dense with high-value information and the purpose is front-loaded before the mechanism details. Every sentence earns its place, including the migration, dedupe, and idempotency notes. However, it is a single punctuation-heavy wall of text with multiple emphasized phrases, which reduces scannability relative to a structured multi-sentence layout.

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 5-parameter tool with no annotations and no output schema, this description covers an exceptional amount: the full dual-entry mechanism, defaults, migration, dedupe, idempotency, and anti-patterns. It falls slightly short of a 5 because it does not describe what the agent will receive back after invocation (no return-value note compensates for the missing output schema), nor does it cover failure cases like a missing granting feature.

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 the baseline is 3; the description adds genuine value on top by explaining the end-state interplay between parameters — how spellIdentifier can be imported from the compendium and become always prepared, how grantedBy hosts the activity and names the Additional Spells entry, and how uses/recoveryPeriod default to 1/long rest. This connective tissue helps the agent reason about the parameters as a system rather than isolated fields.

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 states a specific verb and resource — 'Grant cast without a spell slot, N per rest' on a D&D 5e actor via the 'native 2024 way' — with concrete examples (Magic Initiate, Favored Enemy, lineage grants). It specifies the resulting two sheet entries in detail, making it unmistakable what the tool accomplishes and clearly distinct from siblings like add-feature or manage-activity.

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 when the tool applies: granting free-cast abilities through native 2024 features and migrating the legacy shape. It includes an explicit never-do-this instruction that prevents the obvious wrong implementation. However, it never names an alternative sibling for comparison, so an agent comparing it to add-feature or manage-activity must infer the boundary from the mechanism described.

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