write_card

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

With no annotations, the description must carry the whole behavioral burden. It does disclose important traits: create-mode refusal to overwrite and the narrow, partially destructive scope of update_recent. It says nothing about permissions, what happens when update_recent targets a nonexistent card, or how refs/aliases create links, leaving meaningful gaps.

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?

Front-loaded with the action, then a compact labeled glossary; nearly every fragment carries information. It reads as terse shorthand rather than prose, but nothing is redundant and the mode caveat is placed last where it belongs.

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 7-parameter, nested-object mutation tool with an output schema and no annotations, the description covers the hard parts (kind taxonomy and per-kind field structure). Remaining gaps are edge-case error behavior and link semantics, which are secondary given the return shape is documented elsewhere.

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 0%, so the description must document all 7 parameters, and it largely does: kind with its enumerated values, key as file name and default title, fields as section->text with per-kind section names, plus keywords, aliases, refs and mode. This is substantially more meaning than the bare schema titles provide.

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 opening 'Write a card' states a specific verb and resource, and the elaboration on kind/key/fields makes the object of the write unambiguous. It does not explicitly name read_card/list_cards as the alternatives, so it stops short of full sibling differentiation.

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?

Mode semantics are spelled out precisely: create refuses to overwrite an existing card, while update_recent rewrites only the recent section (followup for events) of an existing card. That is clear when-to-use guidance for the two modes, though there is no guidance about when to prefer this over the read/list siblings.

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