object_patterns

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

The description adds valuable context beyond the readOnlyHint/openWorldHint annotations: validate returns FP001-FP010 violations and is fast/offline, analyze recommends via Microsoft decision tree, and spec provides structure details. However, it omits the 'repair' action (only present in the action parameter enum/description), which is a minor transparency gap.

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 well-structured with bullets per domain and action. Each sentence adds useful information (timing, output, constraints) and is front-loaded with the core purpose. Despite its length, it is efficient for the tool's complexity.

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?

The description covers the main actions (analyze, spec, validate) with return values and usage timing, plus the table domain. The only missing piece is the 'repair' action, which is only documented in the schema's parameter description. Given the rich schema, this is a minor omission; otherwise, it is complete.

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?

With 100% schema description coverage, the baseline is 3, but the description adds depth by explaining the domain parameter (not free-form, belongs to get_knowledge) and highlighting the recommend object as preferred for new forms. It does not fully repeat the schema but complements it.

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 clearly states the tool is a 'Pattern toolkit' for D365FO tables and forms, with specific sub-purposes for each domain (table patterns, form analysis/spec/validation). It distinguishes itself from siblings by explicitly noting that concepts like 'number-sequence' belong to get_knowledge, not here.

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 explicit when-to-use guidance: for a new form, pass recommend for pattern analysis; for spec, 'Call after analyze, before building'; for validate, 'Call before action=create on d365fo_file'. It also contrasts with get_knowledge, making the choice clear.

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