add_analyzer

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

With no annotations, the description carries the full burden, and it does so well. It discloses the config-file write, optional restart, replace behavior, channel-sharing permission via allow_overlap, and the critical UNIO SIGSEGV risk gated behind allow_crashy. This gives an agent a realistic sense of side effects and hazards.

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 front-loaded with the core purpose and then organizes parameter details in a compact, scannable format. Every sentence adds useful information, and the UNIO crash warning earns its place as critical safety context.

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 tool with 8 parameters, no annotations, and no output schema, the description is remarkably complete: it covers side effects, plugin selection, channel order, overlap, replacement, and crash risk. The main gaps are the undefined format_id parameter and the slightly cryptic 'After restart: start() -> export_decoded(analyzer=slot)' line, which could more explicitly state what the tool returns.

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%, but the description compensates for most parameters: plugin, channels with concrete per-plugin formats, parameters, allow_overlap, replace, and allow_crashy are all explained. However, format_id is left unexplained, and restart is only indirectly covered by 'optionally restarts', so the compensation is not complete.

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 states the action ('Add a built-in decoder') and the concrete effect ('writes vis.config's <analyzers> and optionally restarts KingstVIS'). It clearly distinguishes this from sibling tools like remove_analyzer and list_analyzers, and gives enough detail to know exactly what resource is being modified.

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 gives clear context for when adding an analyzer is appropriate, including the script-control/no-GUI intent and a post-add workflow ('start() -> export_decoded(analyzer=slot)'). It references list_analyzer_plugins as the source for valid plugin names but does not explicitly state when not to use this tool or mention alternatives like raw_command.

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