declarations

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

With no annotations provided, the description carries the full burden, and it delivers: 'View' signals read-only access, 'addressed to you' reveals authorization scoping, and the explicit routing tells the agent exactly where side effects will happen when it acts on a result here. It also discloses that the response set is filterable/combinable. Minor deduction: it doesn't explicitly state what fields or status the response contains (e.g., whether already-answered actionables still appear), which would have made this a 5.

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?

Three sentences, each carrying load: (1) what it shows and where responses route, (2) what it deliberately excludes and where those go, (3) parameter documentation with default. It's longer than most descriptions, but every clause serves a differentiation or routing purpose. Slight deduction for the length – though in this case it's earned density, not bloat.

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 simple filterable list tool with 2 parameters and no nested objects, this is close to complete. It covers filtering behavior, defaults, exclusions, and routing responses. There's no output schema to rely on, so the description could have briefly mentioned what fields the returned actionables contain (e.g., who sent the invitation). That said, the description itself states what the tool returns ('pending... actionables'), and the agent has enough to call it correctly and interpret results.

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% (only `box` and `api_key`), both self-explanatory even from bare schema. The description adds value by explaining the `box` semantics ('received', 'sent', 'both') in the context of actionables rather than just an enum list, and states the default explicitly. It doesn't over-explain `api_key`, which is correct.

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 + resource ('View pending alliance actionables'), then elaborates with the two concrete types: 'invitations and join requests'. It explicitly names the sibling tools it is NOT (declare_war, propose_pact, issue_ultimatum and the four response tools), making differentiation from the ~85 siblings trivial. This is the gold standard of purpose statement.

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?

Justification: Goes beyond vague usage context to name the exact alternative tools for each exclusion: 'wars are declared (declare_war), peace is a NAP pact (propose_pact), coercion is issue_ultimatum.' It also maps the four response endpoints (accept_alliance_invite / decline_alliance_invite / accept_join_request / reject_join_request) to the actionables this view surfaces. An agent never needs to guess which sibling to call next.

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