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

Annotations only declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true); the description adds real substance on top: the exact content allowlist and denylist, the hard restriction on company/archived projects, and the mode switch where remove:true detaches the project from the code. It does not explain what a successful call returns or whether repeated calls create duplicate codes (relevant given idempotentHint=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 verb and core action are front-loaded, but the body is three very long, clause-heavy sentences that mix allowlist, denylist, prerequisites, and mode switching in a single run. Nothing is truly filler, yet the mode logic (share vs remove) would be far easier to act on if separated from the content-restriction prose.

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 six-parameter, non-idempotent sharing tool with no output schema, the description covers the important decision points: when to call it, what may and may not be shared, the pre-call confirmation, and how share/remove change behavior. Missing are the shape of the result (presumably the new code) and failure behavior when a project is archived or the code is invalid.

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?

With 67% schema coverage, the description still adds meaning: it explains that omitting 'share' creates a new code while supplying it targets an existing one, that 'remove: true' detaches the project, and it expands the facets enum with per-facet detail (gotchas including how to avoid them, grabaciones only when requested). 'label' is covered only indirectly via 'dile en una línea qué verá la otra persona', and 'project' carries no extra detail beyond the schema.

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 opens with a concrete verb and resource: adding facets of a user's project to a share code, and it enumerates the facet types (gotchas, runbooks, formatos, aprendizajes, decisiones, grabaciones). It also distinguishes its three modes (create new code, add to an existing code, remove a project from a code). It does not name a sibling tool, but the scope phrase 'en el proyecto de práctica de una skill' implicitly separates it from share_brain/share_skill.

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 trigger condition: 'solo cuando él lo pida', plus a required pre-step ('Antes, dile en una línea qué verá la otra persona'). Clear exclusion conditions are stated: no tasks, state, sources, proper names or metric readings, and nothing from company or archived projects because 'no hay forma'. It stops short of naming an alternative tool to use when those exclusions apply.

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