tg_stories

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

With no annotations, the description carries the transparency burden. It discloses a critical privacy behavior: reading the list does not notify owners, only mark_read does, and it is off by default. It also discloses that download saves media to disk and returns paths. This is adequate, though it could mention whether any other server-side state changes occur and what happens with the 'limit' parameter if the feed is paginated.

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?

The description is well-structured and appropriately sized. It front-loads the primary purpose, follows with a crucial privacy caveat, a helpful cross-reference to a sibling tool, and a concise parameter list. Every sentence adds value and there is no redundancy or fluff.

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 list/feed tool with an output schema, the description covers the essential aspects: what it returns, how to narrow scope, the read-receipt side effect, and download behavior. All four optional parameters are explained. The output schema handles return-value details, so the description does not need to restate those. It is complete for the tool's complexity.

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%, but the description fully compensates with a clear Args block. Each parameter (peer, mark_read, download, limit) gets a semantic explanation beyond its type and default. For example, peer notes 'omit for the whole feed' and mark_read warns that the author will see the user in their viewer list. This is exactly the value needed beyond the raw 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?

The description clearly identifies the resource (Stories) and the scope: either the global feed of who has a story right now or a single person's stories. It distinguishes itself from sibling tg_view, which shows a specific photo story as an image, implying tg_stories is for listing. The verb is implicit but the meaning is unambiguous.

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 gives clear guidance on the mark_read parameter ('flip it on solely when the owner asks to') and references tg_view as an alternative for viewing a specific photo story. However, it does not explicitly state when to use tg_stories vs a broader alternative like tg_media, nor does it provide exclusions for cases where the tool should not be used.

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