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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds real behavioural context: one method per call, default einfach, the precondition on existing quality scores, the responsibility boundary with the contracting authority, and the legal framing (§ 127 GWB, § 58 VgV, UfAB 2016). It also names key output fields despite there being no output schema.

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?

Well front-loaded with purpose and methods first, but it is long and repeats the quality-scores precondition twice ('existing quality scores' / 'quality scores have to exist already' / 'Evaluating quality ... remain with the contracting authority'). The example-questions block adds bulk without new information.

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 5-parameter analytical tool with no output schema, the description supplies everything needed: method selection, preconditions, defaults, legal basis, and the key output fields (sieger, zeilen[] with kennzahl and rang, sensitivitaet, legal_basis). Nothing an agent needs to invoke or interpret the tool is missing.

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 100%, so the baseline is 3, but the description goes further: it explains the cross-parameter relationship ('percentage weights ... correspond to gewichtet with gewichtLeistung=60') and ties each enum value to a real-world scenario, which the schema alone does not do.

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 ('computes the score and ranking of bids under the chosen UfAB scoring method') and immediately enumerates the three method variants, so an agent knows exactly what this tool produces. It is clearly distinct from siblings like vergabe_statistik or verfahrenswahl_ermitteln.

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?

Maps typical user phrasing to concrete method choices ('Preis 40 %, Leistung 60 %' → gewichtet; 'best quality per euro' → einfach; 'leading group plus tie-break' → erweitert) and states the precondition that quality scores must already exist. It also draws the scope boundary that quality assessment and the award decision remain with the contracting authority.

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