fonzip_donations

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false; the description's mention of silme and olusturma (delete/create) is consistent with those, so there is no contradiction. But the description adds no behavioral context beyond the annotations: no note on destructive scope, no side effects (e.g., creating a donation can auto-create a user via member_id), no auth requirements, and no mention of the payment_method_select 'card' API restriction hinted at in the 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?

A single dense sentence with no wasted words; the resource name and its most important constraint (date range required for listing) come first, and the semicolon-separated catalog efficiently covers the full action surface. It is compact, though the packed Turkish list functions more as a tag summary than a structured explanation.

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 74 parameters, 14 actions, and no output schema, this is an extremely complex tool, yet the one-sentence description does not orient the agent to the dispatch pattern (action is required and determines which params apply), does not differentiate the list variants (list vs. list_micro vs. list_categories vs. list_donation_forms), and gives no sense of what report covers. The rich schema compensates heavily, but the description alone is not complete enough for safe selection and invocation.

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% — every one of the 74 parameters carries a description with per-action qualifiers in brackets (e.g., '[list, list_micro] ordering'). Per the rubric, this earns the baseline 3 even though the tool description itself adds zero parameter-level meaning. The schema fully compensates for the description's silence on parameters.

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 Turkish description identifies the resource (donations) and enumerates the operations: listing (with a mandatory date range), detail, create, delete, report, plus donation categories, micro donations, pages, and forms. This distinguishes it from sibling tools by domain. However, it reads as a capability catalog rather than a crisp purpose statement, and the full scope only emerges from the 14-value action enum.

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 only usage guidance is the embedded constraint that listing requires a date range. There is no statement of when to prefer this tool over siblings (e.g., fonzip_monthly_donations for recurring donations vs. the recurring filter here), no exclusions, and no alternatives named. The action enum provides structure, but the description itself offers no selection guidance.

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