runrunit_create_comment

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

With no annotations provided, the description carries the full burden, and it discloses two non-obvious behaviors: Markdown is not accepted (plain text and raw URLs only), and the evidence-capture pipeline must run via the registrar-evidencias skill before this tool is invoked with the enriched text. It does not cover response or failure behavior, but the mutating trait is evident from the verb and the described workflow.

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?

Three sentences with the purpose front-loaded, the format constraint second, and the conditional workflow rendered as a compact numbered list. Every sentence earns its place, and nothing merely repeats what the input schema already states.

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 4-parameter create tool with no annotations and no output schema, the description covers purpose, formatting constraints, and the conditional evidence workflow thoroughly enough for correct invocation. The main gaps are minor: no return-value description and no explicit routing to the create_external_comment sibling when the comment should not be attached to a task.

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 100%, so the baseline is 3, but the description adds genuine meaning: it constrains the text parameter's format, and it specifies the exact enrichment format ('Antes: <url>' / 'Depois: <url>') and the step-by-step procedure for the url_antes/url_depois pair, going beyond the schema's brief 'append to text' note. It also clarifies that the enriched evidence block belongs in the text parameter.

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 a specific verb (create), a resource (a comment on a task), and a platform scope (Runrun.it), which is immediately differentiable from the sibling comment tools (update_comment, delete_comment, list_task_comments, get_comment, create_external_comment). Even without naming an alternative, 'Create a comment on a task in Runrun.it' pinpoints the inline-comment creation role precisely.

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 operational context: a plain-text/raw-URL format constraint and an explicit conditional workflow for when url_antes and url_depois are both present, with numbered steps for the evidence pipeline. It stops short of a 5 because it never explicitly names alternatives or states when-not-to-use, but the conditions ('when both are provided') are unambiguous.

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