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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the bar for disclosure is lower and the description is consistent with them ("Put ... on the map" is a write, not destructive). The action enumeration adds real structural context, but nothing is said about idempotency, what existing state backup/import_audit touch, or side effects of session_start. Adequate, not rich.

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 one-line purpose is properly front-loaded, but the action catalogue is a dense run-on with inconsistent punctuation and a garbled trailing sentence ("query actions says what each does"). Information-dense yet poorly structured for scanning.

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 polymorphic dispatcher with a freeform params object, no output schema and three actions requiring different inputs, the description covers enough to attempt a call and defers the rest to query. However the deferral means an agent cannot invoke most actions correctly without a second round-trip, and nothing explains return behavior or the actor field's role.

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 only 33% and params is an untyped freeform object with no documented properties, so the description carries most of the burden. It does that well by listing every action with its parameter names and marking optional ones with "?", which is meaningful information absent from the schema. It stops short of explaining what individual params mean (surface, cwd, remote, rate, planned), keeping it from a 5.

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 gives a concrete framing ("Put something on the map: an item and its links, or a record of what happened") and then enumerates the concrete actions it dispatches to (session_start, picture_put, backup, import_audit, time.log, time.invoice_draft). An agent can tell this is a write/dispatch tool. It does not differentiate itself from siblings that sound adjacent, notably draw and change, so it falls short of a 5.

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?

"Call with the action and its params" plus the action list implies how to invoke it, and the closing pointer to query actions gives a route to per-action documentation. There is no when-to-use-this-vs-draw/change guidance and no statement of which action fits which situation beyond the action names themselves.

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