obs_filters

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

With no annotations, the description must disclose behavioral traits. It indicates the tool can mutate state ('or add one') but provides no details on consequences (e.g., whether adding overwrites existing filters, requires specific permissions, or affects current settings). It also does not mention that the listing operation is read-only or what response format to expect. The lack of any behavioral context beyond the action itself is a significant gap.

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 concise: one sentence stating the core action, followed by a semicolon-separated list of useful filters with brief parenthetical justifications. Every part adds value—the filter names are actionable tips for common use cases (noise suppression, gating, chroma key, async delay). There is no fluff or repetition, making it efficient and easy to scan.

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?

Given the tool's moderate complexity (4 parameters, dual functionality, no output schema), the description covers the main actions and imparts helpful filter-kind examples, but lacks critical details: it does not state that adding requires both kind and name, does not clarify that 'sourceName' is always needed, and does not describe return values for listing. It is adequate for basic usage but leaves the agent to infer important operational details, especially for the add operation.

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 0%, so the description must compensate. It indirectly explains 'addFilterKind' by providing a list of useful filter kind strings with parenthetical hints (e.g., 'RNNoise mic cleanup'). However, it does not clarify that 'addFilterName' is required when adding, nor does it explain 'addFilterSettings' or that 'sourceName' is always required. The examples aid but leave the add process incomplete, so it only partially compensates for the missing schema descriptions.

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 description clearly states the dual purpose: 'List filters on a source, or add one.' It uses specific verbs ('List', 'add') and identifies the resource (filters on a source). It distinguishes itself from sibling tools like obs_filter_get (which retrieves specific filter settings) and obs_filter_remove by covering the listing and adding operations, making it unambiguous when this tool applies.

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 implies general usage for listing or adding filters, but does not explicitly compare with alternatives. It provides practical guidance by listing useful filter kinds with explanations (e.g., 'noise_suppress_filter_v2' for mic cleanup, 'async_delay_filter' for sync lag), which helps when adding. However, it lacks explicit when-not-to-use instructions or mention of sibling tools like obs_filter_get or obs_filter_remove for other filter operations.

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