get_card

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds a genuinely non-obvious behavioral fact beyond that: evidence fields are untrusted source data, a prompt-injection style warning an agent would not otherwise know. It still omits permission requirements and error behavior, keeping it below a 5.

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 short sentences, front-loaded with the core action and followed by the trust caveat. Nothing is padded or repeated, and every clause carries information.

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?

An output schema exists, so return values need not be explained, and the untrusted-data note is a strong addition. However, a tool with an undocumented include_deleted flag and no stated error or permission behavior is only minimally complete for an agent that must decide how to call it.

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 carry the parameter burden and does not. card_id is self-evident from its name, but include_deleted (default false) is never mentioned, leaving its effect — whether soft-deleted cards are returned — undocumented anywhere.

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?

"Read a card and its revision" gives a specific verb and resource, plus the notable detail that a revision is returned alongside the card. It is distinguishable from siblings like list_cards or manage_card by its single-card read framing, though it never explicitly contrasts itself with them.

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?

There is no when-to-use guidance at all: no statement of when to prefer this over list_cards, recall_candidates, or get_recommendation, and no note about prerequisites such as knowing a card_id. Usage is only inferable from the word "Read".

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