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

Annotations only declare the write/safety profile (readOnlyHint=false, destructiveHint=false, non-idempotent), so the description adds real value by explaining the staging lifecycle: the item lands in Capture and is sorted later, and the link travels with the item during triage. That post-creation behavior is not derivable from any structured field.

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?

Two sentences, front-loaded with the core action before the web-page special case. Slightly compressed phrasing in the second clause ("le lien suit l'élément quand on le trie") requires a re-read, but nothing is redundant.

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 four-parameter, fully documented write tool with annotations present and no output schema, the description covers purpose, the triage lifecycle and the url/content interaction. It could say more about what the tool returns or about the Capture list itself, but nothing essential for a correct call is missing.

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 goes beyond per-field documentation by explaining the relationship between url and content: when a page is captured, content should express why it is being kept, and the url is attached to the item. That combination rule is not stated in 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?

"Capturer rapidement une idée dans Capture, à trier plus tard" names a specific verb (capture), a target (the Capture inbox) and a deferral model (sort later), which distinguishes it from a direct create. It stops short of naming a sibling such as dandori_create_note, so the differentiation is inferred rather than stated.

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 implies the right context — fast, low-friction capture with triage deferred — and explains the web-page case where a url accompanies the capture. It never says when to prefer this over creating a note or task directly, nor whether Capture items can be captured without a url at all.

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