align_capture

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this is a non-destructive write; the description adds that captured decisions populate a cross-tool graph and enable relationship detection. It does not say what happens on a duplicate capture, whether the call is idempotent, or what identifiers or confirmation come back — meaningful gaps for a write tool. With annotations covering the safety profile, a 3 fits.

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, front-loaded with the action and supported sources, with the rationale trailing. The clause about the graph staying current and relationships being detected is slightly padded but does carry justification for calling the tool, so it earns most of its space.

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 one-parameter capture tool with annotations and no output schema, the description covers what it accepts and when to call it. The remaining gap is post-call behavior — whether a decision ID or confirmation is returned, and what happens with unrecognized or duplicate input — which the absence of an output schema makes more noticeable.

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% and the single "input" field is documented as "URL or text content," so the baseline is 3. The description earns a bump by enumerating which URL shapes actually parse (Slack, Jira, GitHub, Confluence) versus raw text, which tells the agent what forms are acceptable in a way the schema does not.

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 ("Capture a decision") and enumerates the accepted source types — Slack thread, Jira ticket, GitHub PR, Confluence/doc URL, raw text — which makes the tool's scope immediately legible. It stops short of naming a sibling like align_backfill or align_sync to draw the boundary, so differentiation is left to inference.

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 this whenever a decision gets made in conversation" gives a clear triggering condition, and the stated payoff (keeping the cross-tool decision graph current) explains why. There is no guidance on when NOT to use it — e.g. whether bulk historical decisions should go to align_backfill instead — and no prerequisites or duplicate-handling advice.

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