diana_keywords

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description adds that the data comes from the local installation schema directory, which explains the closed-world read profile, and it discloses the shape of returned records (title, unit, domain, default, allowed values). It does not discuss result ordering, truncation behavior when limit is hit, or what happens on a miss — hence not a 5.

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 statement, then the categories served, then the Args block — a predictable structure that scans well. The bracketed-directory sentence is slightly dense but earns its place by explaining how to build a setParameter path; otherwise there is no 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?

There is no output schema, and the description compensates by describing the fields an entry contains and showing the bracket notation that encodes path structure. Combined with the explicit pointer to diana_parameters for existing item paths, an agent has enough to call this correctly; only edge behavior (no-match, limit caps) is left unstated.

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 carries the full burden and largely does: query is defined as 'words or keywords' with five worked examples, and limit as 'number of entries to return'. It adds real meaning over the bare schema (the examples clarify that either prose terms or raw keyword tokens are accepted), though it omits any hint about the default of 12 or sensible limit ranges that the schema's default value alone implies.

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 names a specific verb and resource ('Look up DIANA data-model keywords in the installation's schema (lib/SCHEMA)') and then enumerates exactly which kind of lookups it serves: material classes for addMaterial, geometry/element classes for addGeometry/setElementClassType, and load/support parameter metadata. Concrete example tokens (CONCR, TSCR, SHEET, MEMBRA, PLSTRA, AXISYM) make it distinguishable from diana_parameters and the manual-search siblings at a glance.

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?

It states when this is the right tool ('The manual does not list these keywords' — so use this instead of the manual tools) and names an explicit alternative with its condition: 'use diana_parameters to see the exact paths of an existing item'. That is a clear when-to-use / when-to-use-something-else pair rather than implied guidance.

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