scan_plugin_catalog

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

Adds real behavior beyond the annotations: the scan is incremental and resumable, exposes a 'remaining' counter the caller must poll, and quarantines modified binaries (broken signature, R2R imports) as excluded and never loaded. That last point is important safety context the annotations (readOnlyHint=false, destructiveHint=false) do not convey.

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?

Dense and front-loaded: purpose first, then resume semantics, then retry behavior, then the excluded-binaries caveat. Every clause carries information, though the line-broken phrasing within a single sentence is slightly harder to parse than short discrete sentences.

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?

An output schema exists, so return values need not be explained, and the resume/retry loop is well covered. However, for a long-running, budget-bounded scan, the undisclosed 'only', 'force', and 'budget_seconds' parameters leave an agent guessing about scope and time limits.

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 carry the parameter burden, but it only explains retry_failed. The 'only' filter, 'force', and especially 'budget_seconds' (which clearly bounds scan time and is essential for an incremental long-running job) are left entirely undefined.

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?

Specific verb+resource: profiles installed VST3 plug-ins, capturing every parameter, presets, and a semantic role (eq, compressor, reverb, piano). The phrase 'outside Live' and 'not just what Live exposes' carves out a clear niche versus Live-facing siblings, although it never names list_plugins, find_plugins, or expose_plugin_params directly.

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?

Gives concrete operating instructions: resume from where it stopped, call again while 'remaining' > 0, and use retry_failed after fixing/activating a plug-in. What is missing is an explicit statement of when to prefer this over find_plugins or list_plugins, or when not to run a scan at all.

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