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

With destructiveHint=true and openWorldHint=false already in annotations, the bar is lower, and the description adds real behavioral context: the freed percentage is not given to anyone else, the total will usually fall below 100% until reallocated, and the tool gets refused once filing begins. It does not cover reversibility or permission requirements, but the added context meaningfully exceeds 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?

Three sentences with no filler: the core action and its results come first, the ownership-total consequence second, and the refusal condition last. Every clause earns its place, and the most decision-relevant 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?

For a destructive two-parameter mutation with an output schema and annotations already declaring the destructive hint, the description covers the behavioral essentials: what is removed, what the report contains, the cap-table consequence, and a refusal condition. Minor gaps include irreversibility, whether the sole shareholder can be removed, and auth requirements, but these are not critical given the tool's moderate complexity.

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 100%, so the baseline is 3 even without extra param detail. The names formationId and shareholderId are self-explanatory, and the description reinforces that shareholderId is the owner being removed. It does not add constraint-level detail (e.g., whether the last shareholder can be removed), so it meets but does not exceed the baseline.

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 opens with a specific verb and resource — 'Removes one owner from a formation' — and adds its observable effects (reporting remaining count and ownership total). This distinguishes it clearly from siblings like formation_add_shareholder, formation_update_shareholder, and formation_set_share_structure, so an agent can tell them apart without opening schemas.

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?

The description provides clear context: it is the tool for removing a single owner, and it gives a strong when-not constraint ('Refused once the filing is under way'). It also explains the consequence that the freed percentage is not reallocated, implying a follow-up reallocation step, though it stops short of explicitly naming alternative tools for that follow-up.

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