Milk Agency · Ad-hoc-Anfragen (Videoschnitt)

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

Annotations already disclose readOnly=false, openWorld=true, idempotent=false, and destructive=false. The description adds critical behavioral context beyond that: the server sends a confirmation link, the request becomes public only after the click for 24 hours, name and email are never published, and agb/rechte are consent declarations.

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-loads the core action and then details the confirmation flow, privacy, and consent requirements. The English summary at the end partially repeats the opening sentence, which is slightly redundant but still useful for non-German readers.

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 complex tool with 19 required parameters and no output schema, the description covers workflow and consent well but leaves many field-level semantics unaddressed. It is adequately complete for the confirmation and privacy behavior but thin on how to populate most required parameters.

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 only 26% for 19 parameters. The description explains only a few fields (agb, rechte, name, email) and their privacy or consent meaning, leaving most required parameters (titel, kategorie, budget, leistungen, etc.) without added semantic guidance beyond their titles and enums.

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 (einstellen) and resource (kostenlose Ad-hoc-Anfrage für Videoschnitt oder Postproduktion), and distinguishes this create action from siblings like anfragen_auflisten and auf_anfrage_bewerben by emphasizing it posts a new request on behalf of a person without an account.

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?

Provides clear context for use: free, no account, on behalf of a brand, agency, or creator. However, it does not explicitly name alternatives or state when not to use this versus formular_link_erstellen or other siblings.

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

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

Annotations already assert readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the return-field inventory and the fact that filters are optional, but says nothing about result count, ordering, pagination, or whether all open requests or only a subset are returned — the bar is lower with annotations, but this is thin.

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 verb and resource, and the optional-filter note is placed last where it belongs. The first sentence is a long comma-separated field list and the trailing English sentence is a trimmed restatement, but overall there is little waste.

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-optional-parameter, read-only listing tool with no output schema, the description usefully enumerates what each result contains (scope, formats, services, delivery time, fixed price, turnaround) and notes DACH coverage. Ordering/pagination details are the only real gap and are minor here.

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 0%, so the description must carry the burden, and it does map both parameters to their meaning ('nach Art' = kategorie, 'Mindestbudget' = budget_min). However it does not explain the seven enum categories or what the budget threshold filters against, so the compensation is partial.

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 ('Listet') plus resource ('offene Ad-hoc-Anfragen für Videoschnitt und Postproduktion') and geographic scope (DACH), and it enumerates the fields the listing exposes (Umfang, Formate, Leistungen, Lieferzeit, Festpreis). It is clearly distinguishable from the write-oriented siblings (anfrage_einstellen, auf_anfrage_bewerben), though it never names them explicitly.

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?

'Optional nach Art oder Mindestbudget gefiltert' signals that both filters are optional, which is useful invocation context, but there is no explicit when-to-use/when-not guidance and no pointer to an alternative tool for a different view of the same requests. Usage is implied rather than stated.

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

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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false, so the safety profile is covered. The description usefully adds the side-effect destination ('his reply goes to the specified e-mail'), but omits irreversibility, auth/rate-limit considerations, and what (if anything) is returned.

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 sentence with the core behavior, followed by the zusage clarification. The English restatement is somewhat redundant but short, and no sentence wanders.

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?

Covers the primary flow for a 5-required-parameter mutation with no output schema, but leaves open what happens on failure, whether the applicant sees a confirmation, and the meaning of several parameters. Adequate but with clear gaps.

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 low (17%), so the description must compensate. It meaningfully identifies 'id' as the request ID and pins down 'zusage', but does not explain 'name', 'nachricht', or the optional 'portfolio' link, leaving half the parameters to the bare schema titles.

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 + resource: it sends an application ('Bewerbung') for an open request ('offene Anfrage') by e-mail. This action is clearly distinct from the siblings that create/list requests or produce form links, so an agent can distinguish it without opening the 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?

The description explains what happens but never states when to pick this tool over alternatives. No mention of prerequisites (e.g. that the request must still be open) or of the sibling tools. Usage can only be inferred from the verb.

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

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

The annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description nonetheless adds value beyond that: it clarifies that personenbezogene Angaben (Name, E-Mail) are deliberately left for the recipient to fill in, so the prefill is partial, and reaffirms that nothing is persisted.

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?

Two front-loaded German sentences covering what it does, who fills the rest, and the no-side-effect guarantee, followed by a compressed English one-liner. No filler; the bilingual restatement is mildly redundant but cheap.

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 15-parameter, zero-required tool with no output schema, the essentials are covered — it returns a prefilled link and persists nothing. However, it never says what the returned link looks like or what happens when only some of the many optional fields are supplied, leaving the agent to guess at the intended 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 only 27% across 15 parameters, so the description is expected to compensate and it does not — it mentions no individual field. Enum values and titles carry some meaning (e.g., Formate, Kategorie), but which fields are relevant for a given request and how partial input behaves is left entirely undocumented.

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 (erstellt) and resource (Link zum Formular für Ad-hoc-Anfragen) plus scope (vorausgefüllt mit übergebenen Angaben). The clause 'Sendet und speichert nichts' behaviorally separates it from the sibling anfrage_einstellen, though no sibling is named explicitly.

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?

Usage is implied rather than stated: the agent can infer this is the pre-submission step where a requester fills in their own name and email. There is no explicit 'use this when / not when' guidance and no reference to when anfrage_einstellen is the better call, which is a real fork given the sibling set.

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