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

With no annotations supplied, the description carries the full burden and does it well: it discloses that entries are permanent and cannot be edited or deleted by the agent (only the user, via the web), that logs themselves cannot be deleted, and that date and author are auto-recorded. It also warns against including secrets and documents markdown plus $[note:id:title] / $[environment:id:name] chip syntax. Minor gap: no stated length/rate limits or failure behavior.

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 critical constraint (one permanent line) is front-loaded, and the note-vs-log distinction, linking flow, and expedient exclusion are cleanly delimited. It is long for a single-append tool and reiterates immutability more than once, but nearly every sentence resolves a real ambiguity.

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 three-parameter mutation tool with no annotations and no output schema, the description covers what gets stored automatically, what cannot be undone, formatting options, and how the entry relates to notes and environments. An agent can call it correctly and write a compliant entry from this text alone.

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 100%, so each of the three parameters is already documented in the schema, setting the baseline at 3. The description adds modest meaning beyond it: content must be a single self-sufficient line with what/where/result and optional chips, and the agent field should name model and tool (the schema already gives examples of this). logId's meaning is only implied by the surrounding note/log discussion.

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 ("Añade UNA línea al final de una bitácora") plus the shape the appended content must take (qué se hizo, dónde, resultado). It explicitly separates this tool from notes and expedientes, so an agent can distinguish it from sibling concepts without opening other definitions.

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?

Provides an explicit decision rule for notes vs. logs (living documentation vs. immutable chronological history), including a concrete heuristic ("hoy he hecho X" or a Historial/Changelog section belongs in a log). It also gives an ordered workflow with siblings: find via logs_list, create with log_create if absent, and cross-link with chips.

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