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

Annotations only declare write-ish, idempotent, non-destructive, closed-world. The description goes well beyond that by explaining the actual effect: the note itself is unchanged, the mark is stored as search feedback, and on a repeat of the same query the note resurfaces at the bottom flagged as irrelevant. That last sentence explains the consequences of a non-obvious side effect, which is exactly the kind of context annotations cannot supply.

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 short sentences with no waste: what it does, when to invoke it, and what happens afterwards. The consequence — the most decision-relevant fact — is saved for last but the action itself is front-loaded, so the structure works.

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 simple three-parameter feedback tool with full schema coverage and annotations, this is nearly everything an agent needs. The only omission is what the call itself returns, and with no output schema present that is a minor gap given the description already explains the persistent effect of the marking.

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 adds real meaning on top: the id must be a note that came back from search_brain, and the query is the exact search as it was performed (reinforcing the schema's 'tal cual se hizo'). The optional reason field gets no extra treatment beyond the schema, which keeps it from a 5.

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 gives a specific verb and object — recording that a note returned by search_brain was irrelevant to a particular query — and attributes the note to its source tool, so it is immediately distinguishable from note-creation siblings like keep_note or add_learning. An agent knows exactly what it is recording and about which note.

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?

It names two concrete triggering conditions: the user says so, or the agent itself discards the note as inapplicable while reading it. That is clear when-to-use guidance. It stops short of stating when not to use it (e.g. notes not surfaced by search_brain) or naming a corrective alternative, but the surrounding context makes the boundary fairly evident.

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