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

With readOnlyHint=true, the description needs to add non-safety behavior context, and it does: it discloses the four classification outcomes, the detected domain, standard objects, extension lookup depending on D365_CUSTOM_MODEL_PATH, and the effort estimate with reasoning. There is no contradiction with the read-only annotation; the tool is clearly an analysis/classification operation.

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-sectioned and scannable, but it repeats trigger information in both the opening 'WHEN' block and the later 'Triggers' list. The emoji-laden verdict list is useful but adds verbosity. It earns a middle score: organized yet redundant in places.

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 carries the burden of explaining return contents; it does so explicitly by listing the detection domain, standard objects, extensions, effort estimate, and reasoning. It also covers input routing and environmental context for extension detection, making the tool sufficiently fully specified for an agent to invoke 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 description coverage is 100%, so the schema already documents each parameter's role. The description adds extra semantic value by explaining parameter selection strategy, especially the rule to prefer requirementText over re-fetching workItemId after prior analysis, and that requirements overrides the other inputs. This goes beyond the baseline but still leans on schema for basic meaning.

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 clause and then states the core function: 'GAP / FIT CLASSIFIER -- Analyse a D365 F&O requirement... and classify it as one of four verdicts'. It lists the four verdicts explicitly (Standard Fit, Config Fit, Extension Fit, Gap) and describes what the tool returns, making its purpose unambiguous and distinguishable from sibling analysis tools.

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 provides explicit trigger phrases and concrete guidance on when to pass requirementText directly versus using workItemId, including a specific directive: 'do NOT re-fetch with workItemId' when a WI has already been analyzed by ado_analyze_workitem. This gives the agent actionable selection criteria beyond the schema.

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