get_language_reference

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new behavioral context: the no-argument call returns a very large payload (hundreds of KB), an error occurs for undocumented types, and the returned content includes universal rules (color set, titles, categorize-and-color). This is exactly the kind of cost/error/redundancy disclosure annotations cannot carry.

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?

Three dense sentences, front-loaded with the core action before the conditional behavior and the sibling-avoidance note. Every clause carries information; it is slightly long but no sentence is filler.

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?

No output schema exists, so the description must describe return values, and it does: the type section plus universal rules, or the full reference. Error behavior, alternatives, and payload-size trade-offs are all covered, leaving nothing an agent needs to call it correctly.

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 goes beyond it by explaining the effect of the parameter (returns that type's section plus universal rules), the consequence of omitting it (entire reference, very large), and the failure mode (errors for undocumented types, ids via list_chart_types). Only the absence of example id syntax keeps it from a 5.

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 and resource ('Get the DGMO language reference') and precisely scopes the two modes of operation (with vs. without chart_type). It explicitly distinguishes itself from siblings suggest_chart_type and list_chart_types, so an agent can route correctly without opening any 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?

Gives explicit when-to-use guidance ('pass chart_type whenever the type is known'), a when-not ('suggest_chart_type already appends the chosen type's section, so a call here is only needed after the user picks a type or when switching types'), and names the fallback tool for error recovery (list_chart_types for valid ids).

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