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

Annotations declare non-readonly/non-destructive/non-idempotent; the description's real value-add is the authentication and permission requirement, which annotations don't convey. It stops short of the thing that matters most for a non-idempotent upsert, namely whether omitted fields are cleared or left untouched.

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 sentences, zero filler: capability and its variants first, the auth requirement second. Nothing could be removed without losing 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?

Good coverage for an 8-parameter mutation: mode selection, editable fields, and auth are all present. The remaining gap is update semantics and return behavior (no output schema, and the description never says what the call returns or whether a partial update wipes unset fields).

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 100%, so the baseline is 3. The description repeats the salient semantics (id selects update, status values, eta, linked_release) but adds no format, length, or null-handling detail beyond what the schema already documents.

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?

States a specific verb and resource ('Add an item to your LogPulse roadmap, or update one by id') and enumerates the update modes: status transition, ETA change, release linking. That distinguishes it cleanly from read-only siblings like get_roadmap and from unrelated write siblings like publish_release.

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 create-vs-update branch is made explicit ('or update one by id'), which is the main routing decision an agent faces. It also names the prerequisite (an API key with the 'Update roadmap' permission). No exclusion toward a sibling tool or statement of what not to do, so not a 5.

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