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

With no annotations, the description carries the full burden and does it well: it discloses the return behavior (the link is returned once and is not emailed), the exact visibility boundary for the subcontractor (job summary, work address, scope note, upcoming visits, notes - but never prices, customer identity, or other subs), the lifetime semantics (expires_in_days default 90, max 365, until removed), and the permission requirement. The only gap is what happens on a duplicate email or an invalid job_id.

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 action and its two core inputs, then a tightly packed block on the link handoff, visibility, lifetime, and permissions. Every sentence carries distinct information; nothing restates the schema or name.

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?

An output schema exists, so return shape need not be spelled out, yet the description still volunteers the critical fact that the link is shown only once. Together with the permission gate and expiry defaults this is enough to invoke correctly; only duplicate-handling and the remaining optional fields are unaddressed.

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 only 29%, so the description must compensate. It adds real meaning for email ('the one email they will sign in with'), scope_note ('your scope note', visible to them), and expires_in_days (default 90, ceiling 365), but says nothing about trade, contact_name, or company_name beyond the obvious, leaving three parameters semantically bare.

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 ('Add a subcontractor to a job') and narrows it to the essential inputs ('a company and the one email they will sign in with'). This is clearly distinct from sibling operations like subs_list, subs_update, subs_remove and subcontractors_prepare without needing to name them.

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 preconditions ('Owner or office only') and an operational instruction the agent must act on ('Returns a link once; share it with them yourself (Doing Work does not send it)'). It stops short of naming alternatives or exclusions - e.g. when to use subcontractors_prepare or shares_create instead - so it is clear context without explicit routing.

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