get_plugin_profile

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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds what the payload contains, but omits operational traits that matter here: whether the plug-in must be loaded first, whether a profile must be generated via learn_plugin_profile, and what happens if no catalogue entry exists (error vs empty profile).

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 front-loaded sentence that opens with the core purpose and then enumerates contents, with no filler. The parenthetical example ('mix/threshold/decay... -> real parameter names') is dense but earns its place by clarifying the semantic map.

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 the return shape does not need explaining, and the prose summary of contents is a useful complement. However, for a tool whose main input ('name') has an unstated format and whose optional 'parameter_filter' is undefined in both schema and description, the definition leaves real calling ambiguity.

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% for two parameters, and the description compensates for neither. It does not say whether 'name' is a display name, file identifier, or fuzzy match, nor what 'parameter_filter' filters (names, roles, substring vs regex) or that an empty default returns everything.

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 and resource: the 'full catalogue profile of one plug-in', enumerating what the profile contains (parameters with ranges/options, presets, roles, semantic map). This differentiates it reasonably from list_plugins and get_plugin_presets, but the contrast with close siblings like get_device_params, expose_plugin_params, and learn_plugin_profile is left implicit.

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?

There is no explicit when-to-use guidance and no exclusions. The reader must infer that this is a discovery step called before setting parameters (the semantic-map clause hints at that), but the description never names an alternative such as get_device_params for live values or learn_plugin_profile for building a profile.

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