team_insight_save

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose the key trait an agent can't infer — team-wide visibility versus seat-private — and that entries are searchable via team_insight_search. But it says nothing about whether saves are idempotent, how 'supersedes' behaves (archive, overwrite, or linked), whether the body is truncated, or what permissions are needed.

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?

A single dense sentence plus one clause, with the most decision-relevant fact (WHOLE team vs seat-private) in the first phrase. Nothing is repeated from the schema and no words are wasted.

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 5-parameter mutation tool with no annotations and no output schema, the description covers the routing decision well but leaves gaps: no return-value indication (does it yield an id usable in supersedes?), no explanation of supersedes, and no note on duplicate handling. Adequate but not complete.

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 80%, so the baseline is 3 and the schema already documents headline, body, repo, and tags including their length caps. The description adds meaning only indirectly by enumerating the kinds of content that belong in body; the 'supersedes' parameter is left entirely unexplained in both schema and description.

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?

Specific verb plus resource ('Save a reusable finding for the WHOLE team') with the scope delimiter front-loaded, and it explicitly distinguishes itself from team_memory_save ('seat-private'). An agent can pick between the two siblings without opening either schema.

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?

Gives concrete triggers for use ('a trap fixed, a measured number, how something works'), names the alternative (team_memory_save) and the retrieval counterpart (team_insight_search), and adds a downstream lifecycle rule (promote durable ones into docs/wiki/). When-to-use, when-to-use-instead, and what happens afterwards are all present.

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