vedika_conversation

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

With no annotations present, the description carries the whole burden and does well: it discloses pagination behavior (pass data.nextCursor unchanged, continue even after an empty page, stop at null, paginationAvailable=false means no continuation), warns that results are not a snapshot, and notes conversations persist for context continuity. It never states whether delete is irreversible, what TTL defaults to, or what auth is required.

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 purpose, then organized action-by-action, with the pagination rule packed into efficient sentences. Nothing is badly padded, though the trailing 'Free.' is a slightly dangling fragment and the pagination caveats take three sentences to state.

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?

There is no output schema and no annotations, and the description steps in to cover the highest-risk gaps: pagination termination, non-snapshot semantics, lifecycle/creation, and TTL extension. It is still silent on delete irreversibility, TTL defaults for extend, and the shape of the get response beyond 'with stored messages', which a mutation-capable tool with zero annotation coverage should ideally cover.

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 schema already documents limit, cursor, conversationId, and the action enum, giving a baseline of 3. The description adds procedural meaning on top: default 10 / maximum 100, ordered by last activity, and the precise cursor continuation rule (continue after an empty page, stop at null), which is more than the schema's terse 'pass the prior data.nextCursor unchanged'.

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?

Opens with a specific verb+resource ('Manage multi-turn AI conversations') and then enumerates the four concrete operations (list, get with messages, delete, extend TTL). It also distinguishes itself from the sibling vedika_ai_chat by explaining that this tool is where those conversations are managed and that vedika_ai_chat is what creates 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?

It tells the agent which action to reach for in each situation (list for recent activity, get for a specific conversation with stored messages, delete to remove, extend for TTL) and explains the creation path via vedika_ai_chat. There are no explicit exclusions or 'do not use when' conditions, so it stops short of 5.

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