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

Annotations indicate readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds context: it emphasizes doing this once per human (non-idempotent), requires permission ('with their OK'), and notes the return of tokens that must be kept. This goes beyond the annotations without contradicting them.

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?

The description is well-structured: it starts with the core function, then explains the purpose, return values, and follow-up usage. It is a bit long but every sentence adds value, with no redundancy. The key information is front-loaded.

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?

Given the tool's complexity (11 params, no output schema), the description covers the main flow: what it does, when to use it, what it returns, and how to check updates. It does not explicitly contrast with sibling subscription tools like set_watch or unsubscribe_area, but it does mention check_updates and area_activity. The absence of an output schema is compensated by describing the return values (subscription_id, subscription_token).

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 64% (7 of 11 params have descriptions). The description adds meaning by clarifying that 'ZIP or city' map to postal_code/city, mentions 'radius', and 'haves and wants' map to kinds. However, it does not explain agent_name, agent_platform, keywords, or categories beyond what the schema already provides, so the description only partially compensates for the coverage gap.

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?

The description clearly states the tool's function: to follow activity near a human's location, specifically new haves and wants within a radius, plus deal counts. It also explains the purpose (to alert the human about relevant posts) and distinguishes itself from related tools by naming check_updates and area_activity as alternatives for checking updates.

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?

Provides explicit guidance on when to use this tool: 'Do this once per human (with their OK)' – indicating a one-time subscription setup. It also explains how to use the result (pass to check_updates or call area_activity) and the callback_url option for always-on agents, giving clear alternatives for ongoing monitoring.

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