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

Annotations declare non-readonly and idempotent, and the description goes further by enumerating the three possible outcomes (executed/pending/rejected), explaining idempotency_key reuse semantics ('repeating a key returns the original outcome instead of acting twice'), disclosing the dry_run behavior, and noting an agent key is required. This is rich context well beyond the annotations.

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 outcome model, then idempotency, then dry_run, then the auth requirement. Dense and largely waste-free, though the semicolon-chained pending/rejected clauses make it slightly heavy to parse.

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 mutation tool with no output schema and a nested input object, the description covers the outcome states, retry semantics, and dry-run preview, plus the agent-key requirement. The only remaining gap is that valid operation names and input shapes are delegated to tower_capabilities, which is acceptable but worth noting.

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 50%, so the description must compensate: it clarifies idempotency_key with a concrete example ('such as the source message id') beyond the schema note, and explains dry_run's effect ('see the decision without executing'). Operation and input are left to the schema/other tools, so it is strong but not exhaustive.

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: 'Ask Tower to perform an operation on the legacy system.' It clearly differs from siblings like tower_get_action (used only for polling) and tower_capabilities (used to discover operations), so an agent can route without ambiguity.

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 decision-dependent guidance: on 'pending' poll tower_get_action and do not resubmit; on 'rejected' do not retry unchanged. This is a rare case where the description tells the agent precisely when to call this tool and what to do with each outcome.

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