run_tool

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is partly covered. The description adds semantic context about what each sub-tool inspects (definitions, call paths, claims, history), but never says which sub-tools mutate state or what side effects a dispatch can cause, which matters given readOnlyHint=false.

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 opening sentence is front-loaded, but the rest is a dense run-on catalog using inconsistent notation (bare names, {braces} for some optional params, '?' markers) that is hard to scan. The information is dense but poorly structured.

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 10-sub-tool dispatcher with an open-ended 'arguments' object and no output schema, the catalog is the necessary core and is mostly present, but two enum values are undocumented and per-sub-tool argument semantics are terse or missing.

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?

The schema documents 'name' (enum) and leaves 'arguments' as a free-form object with only a generic example, so the description carries the real payload documentation by spelling out each sub-tool's arguments. It falls short of 5 because grep_context and read_context appear in the enum but are never described.

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 lead sentence states a specific verb and resource ('Run ... Verinoda tool') and the enumeration makes clear this is a dispatcher over named sub-tools. However, the phrasing 'one more' is odd and no sibling tool (project_query, analyze, code_check) is referenced, so the agent gets no differentiation from alternatives.

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 catalog implies routing — e.g. 'change_review before editing, {since_last?} after' and 'history_search ... when text came/went' — which helps pick a sub-tool. But there is no guidance on when to call run_tool at all versus the sibling tools, and no explicit exclusions.

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