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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description still contributes real behavioral context beyond them: the filter is deterministic and matches the website feed, it deliberately makes no fit judgment, subcategories are inherited by parent categories, and a missing profile produces an empty result plus a profile_missing flag. It stops short of describing pagination limits or total-count behavior beyond the page cap.

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?

Four sentences, front-loaded with the core definition, then scope defaults, then the empty-profile edge case – each earns its place. The one soft spot is the dangling cross-reference 'with the same knowledge block as search_tenders', which gestures at a concept without explaining it in this definition.

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?

For a two-parameter, fully schema-documented read tool with an output schema, this is complete: scope defaults, page sizing, subcategory inheritance, determinism, and the missing-profile outcome are all covered, and return-shape detail is properly delegated to the output schema.

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 schema description coverage at 100%, the schema already documents `page` (1-10) and every `status` enum value in detail. The description adds only that `status` 'widens' the default open-only scope and that results are capped at 10 per page, both of which are already visible in the schema bounds and defaults. Baseline 3 is appropriate.

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 ('List tenders that pass the user's Tendy profile filters') and immediately pins down what those filters are: categories with subcategory inheritance, regions, and budget range. It also distinguishes this tool from a judgment-based matcher ('does not judge whether the user qualifies'), so an agent knows this is a deterministic profile filter rather than a relevance search.

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?

Gives clear operating context: default scope is open tenders only, `status` widens it, and an account with no profile yields an empty list with profile_missing true. It references search_tenders as the tool sharing the same knowledge block, which implies the sibling relationship, but never states the inverse rule ('use search_tenders for keyword/location queries instead'), so the alternative is only implied.

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