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

Annotations already carry readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, but the description adds three genuinely new behavioral facts beyond them: results come in a paginated envelope where 'next' is a page number or null, natural-person counterparties are redacted, and summing amount_net across results double-counts spend. These materially change how the agent should interpret and use the output.

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 long but dense and purpose-front-loaded: scope first, then filters, then behavioral warnings. The filter enumeration partly restates the well-covered schema, which adds length, but it embeds compound semantics and provenance details that keep nearly every sentence informative. No filler or repetition of annotations.

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 an 18-parameter, zero-required search tool with an output schema and seven siblings, the description covers all the non-obvious ground: cross-source scope, compound filter usage, pagination envelope shape, redaction behavior, and spend-aggregation routing. Since an output schema exists, return-value details are not the description's job, and nothing critical is left out.

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 coverage is 94%, so the baseline is 3. The description earns an extra point by explaining the non-obvious parameter interplay — deadline_after=TODAY combined with status=tender identifies open tenders — and by clarifying that direct_award, single_bidder, and cancelled are published ΚΗΜΔΗΣ facts rather than arbitrary flags. Most individual parameter semantics, however, remain in the schema.

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: 'Search Greek public-procurement acts' across three named sources (Διαύγεια, ΚΗΜΔΗΣ, EU TED). The scope is precise, and the closing instruction to 'use rank_entities or spend_by_cpv' explicitly distinguishes it from sibling aggregation 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?

Explicitly names alternatives with the condition that selects them: 'Do NOT sum amount_net across results to get spend — use rank_entities or spend_by_cpv.' It also gives a concrete compound use case — deadline_after=TODAY + status=tender yields the OPEN tenders a supplier can still bid on — so an agent knows when and how to invoke it.

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