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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the description is not burdened with basic safety disclosure. It adds useful behavioral context: extension lookup only happens if D365_CUSTOM_MODEL_PATH is set, and the tool returns a structured analysis including standard objects, effort estimate, and reasoning. No annotation contradiction exists.

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 and front-loaded with WHEN, followed by classification definitions, return sections, triggers, and an input-mode caveat. It is somewhat long and the WHEN section overlaps with the later Triggers list, but every section carries useful information for a complex classifier tool.

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, so the description must explain return values, and it does: detected domain, standard objects, existing extensions, effort estimate, and reasoning. It also covers all four input modes (project, workItemId, requirements, requirementText) and their relationships, making the tool safely callable without external documentation.

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 100%, so the baseline is 3, but the description adds meaningful usage nuance: it explains that requirements overrides WI and requirementText, and that requirementText should be preferred when a WI was already analyzed. This goes beyond the schema's individual parameter descriptions and helps an agent choose the correct parameter combination.

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 opens with a clear 'WHEN' statement and identifies itself as a 'GAP / FIT CLASSIFIER' that analyzes D365 F&O requirements and classifies them into four defined verdicts. This immediately distinguishes it from generic work item analysis tools like ado_analyze_workitem and effort-only estimators.

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 provides explicit trigger phrases, states when the tool is relevant ('Also triggered by gap analysis or fit/gap classification'), and gives a concrete routing rule: if a work item was already analyzed by ado_analyze_workitem, pass requirementText directly and do NOT re-fetch with workItemId. This is actionable guidance for choosing the right input mode.

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