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

Adds substantial context beyond annotations: bounded read-only provider requests, that the only write is one local commit plus an immutable settlement, that it never writes to the provider or retries/replays, and that it is refused until activation. This reconciles the readOnlyHint=false annotation by explaining exactly what is written.

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?

Front-loaded with the core action and scope, and nearly every clause carries distinct information. It is dense and somewhat run-on with many negative constraints, but not padded.

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 mutating integration tool with no output schema, the description covers the write path, side effects, idempotency behavior, activation gating, required scopes (integrations:write, tickets:write), and the fallback read tool – enough for an agent to invoke it correctly.

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%, so the description carries the burden. It clarifies the provider dimension ('GitHub or GitLab', 'Asana has no status effects') but says nothing about effect_id beyond what its name and pattern imply, so it only partially compensates.

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 (settle/confirm) plus resource (one uncertain GitHub or GitLab status effect) and the mechanism (re-reading the ticket's linked issue). It is clearly distinguishable from siblings like list_ticket_integration_effects_v2 and confirm_ticket_integration_create.

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 explicit conditions for use ('Only when the issue shows the status the effect wrote'), a negative outcome ('otherwise nothing is recorded'), a gating rule ('Refused until the deploy-owned settlement activation'), and names the alternative to read first ('read list_ticket_integration_effects_v2 before another action').

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