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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantive behavioral context beyond them: no vendor calls are made, source text is treated as data, listed integrations are untested, 'docs-reviewed' means documentation review only, and results carry vendorTestingPolicy. These trust and provenance caveats are exactly what an agent cannot infer from annotations.

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 action and scope, and most sentences carry distinct constraints. The vendor-untested point is stated twice ('integrations are untested' and 'tests do not test or certify vendors'), which is mild redundancy.

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?

With no output schema, the description usefully notes that results include vendorTestingPolicy, giving a sense of the return shape, and the caveats cover the tool's likely trust pitfalls. It stops short of describing row/field structure, but for a read-only comparison tool this is largely sufficient.

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?

The description reinforces the ids constraint ('2 to 4 distinct'), matching minItems/maxItems/uniqueItems already in the schema, but adds no syntax or ID-format guidance beyond the schema. The language parameter, which carries the schema's own description, is not addressed at all, so with 50% coverage the description neither compensates nor regresses.

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 with scope: 'Compare 2 to 4 distinct software IDs from the catalog.' It distinguishes itself from the sibling get_software by noting when the full record is needed instead, so an agent can route correctly without opening either 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?

It names an alternative ('Use get_software for the full record') and implies compare returns a summarized/unified view, which is clear context for selection. It does not, however, address when comparison is inappropriate versus search_software or get_review_summary, so usage is clear but not exhaustive.

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