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

With no annotations, the description carries the burden and does add real behavior: it returns a chip link, status changes in shared folders trigger email notifications, the reference graph auto-updates on save, and there are workflow constraints around done. However, it omits some behavioral detail such as auth/permission requirements and whether creation is reversible, so it is strong but not exhaustive for a mutation tool with zero annotation coverage.

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?

Content is information-dense but sprawling and repetitive: the chip linking pattern ($[issue:id:título]) is explained three separate times, and status workflow guidance is interleaved with linking syntax. Front-loading is decent (what it does first), but the wall-of-text could be tightened.

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 create tool with 100% schema coverage and no output schema, the description covers most of what an agent needs: identity, return value, linking, priority, and status workflow. It is somewhat verbose yet still leaves permission/failure behavior implicit, so it is adequate but not perfectly scoped.

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. The description goes beyond the schema by explaining the meaning of each status value (open/in_progress/test/done with nuance about test vs done) and priority selection logic, and by pointing folderId to issue_folders_list and content chips to the linking syntax. It adds useful decision semantics rather than merely restating enums.

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 ("Crea una issue") and immediately defines the concept as work-to-be-done with state, plus what it returns (the $[issue:id:título] chip). It actively distinguishes issues from notes/logs ("Nota = cómo funciona algo; bitácora = qué pasó; issue = qué falta por hacer"), so an agent can tell it apart from siblings like notes_create or log_create.

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?

Explicit guidance on when to use: search first with issues_search/issues_list to avoid duplicates; set status in_progress when starting, test when finishing, only done when verified; revert to in_progress if tests fail; choose priority by user indication or evident severity, default medium; propose vs_open when a task stalls. Names concrete alternatives and conditions for each.

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