describe_options

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

With no annotations the description carries the full burden; it discloses the read-only nature, the bounded first page, the 16-ID cap, distinct IDs for matching research pairs, and that descriptions follow the game's current language. It omits permission/ownership failure behavior, how to advance past the 'first bounded page' (no offset or cursor parameter exists), and ordering guarantees.

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-loaded with the core verb and resource, then kind semantics, then parameter guidance. Dense with no filler, though the clause about research pairs keeping separate IDs is narrow enough that it reads as a special-case note rather than a general rule.

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 3-parameter, no-annotation, no-output-schema tool, the description covers what is returned (names, descriptions, costs, rules) and how to parameterize it. The notable gap is pagination: it says to omit ids for the 'first bounded page' but there is no visible mechanism for subsequent pages, leaving result-set completeness ambiguous.

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%, so the description must compensate, and it largely does: it explains all four kind values by what they return, the ids parameter's default-page-vs-explicit-selection semantics and its 16-item limit, and implies entity_id identifies an owned entity. It does not say what happens when ids exceed 16 or reference non-advertised IDs.

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+resource: read native names, descriptions, costs and rules advertised by an owned entity, and splits the behavior by kind (self = current template, others = advertised research/training/construction options). This is enough to distinguish it from action siblings like research_technology or train_units, though the term 'advertised' is game-jargon an agent must infer.

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 real selection rules for parameters (omit ids for the first bounded page; up to 16 IDs; kind=self vs other kinds) and one exclusion ('No arbitrary template lookup'). It never states when to prefer this tool over the sibling action tools or what to do before researching/training, so usage is implied rather than explicit.

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