company_ex_employeesA company's former employees (position, start and end date) — the record
created when someone is fired via company_fire_employee. Without
company_id, returns every ex-employment row the caller can see (their
own, plus every company they administer).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number, 1-based. | |
| page_size | No | Results per page (max 100). | |
| company_id | No | Only rows for this company. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only, but the description adds meaningful behavioral context: the records are created by company_fire_employee, and without company_id the tool returns every ex-employment row the caller can see, including their own and administered companies. This goes beyond what the schema or annotations convey.
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?
Two sentences with no filler: the first defines the tool's output, and the second clarifies default scoping behavior. The most important information is front-loaded and every sentence earns its place.
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 read-only listing tool with three optional parameters fully described in the schema, the description is complete. It covers what the rows represent, how they are created, and the default scope behavior, so an agent has enough to select and invoke it correctly.
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% with clear per-parameter descriptions, so the baseline is 3. The description adds extra value by explaining the semantic distinction of omitting company_id versus providing it, which is not fully captured by the schema's 'Only rows for this company.'
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 object (former employees), the fields (position, start and end date), and the origin (created via company_fire_employee). The word 'former' distinguishes it from the sibling company_employees, and the firing context makes the purpose unmistakable.
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 gives clear context for when to use the tool and explicitly explains the behavior when company_id is omitted versus provided. It does not name an alternative tool like company_employees, but 'former employees' and the firing provenance make the appropriate use case clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are grouped by domain prefix and mostly target a distinct resource, but there are several near-overlapping read clusters — notably whoami/event_roles/event_my_membership (all answer 'what roles at event X'), submission_get/submission_page, team_open_roles/team_seeking_members, and company_employees/company_roster. The descriptions do an exceptional job of steering ('use this, not that'), so misselection is unlikely, but the sheer number of such pairs keeps this from a 5.
The dominant domain_prefix + noun/verb pattern (event_, team_, submission_, company_, article_) is consistent and readable. Deviations: list_api_endpoints/list_capabilities invert the word order (verb-first) versus event_list/submission_list elsewhere, search and whoami carry no domain prefix, account_how_to_sign_in is a phrase, and read verbs vary between get/list/browse/page/preview.
60 tools is far beyond the 25+ threshold, and the surface is purely read-only — the breadth comes from extremely granular views (22 event_* tools) and many singleton catalogs (event_cities, event_types, event_background_images, article_languages, tag_list, tech_list, company_vacancies) plus six meta/informational tools. The domain is genuinely broad and every tool is distinct, so it reads as heavy rather than chaotic, but the count is still excessive.
The set contains zero write tools — no create, update, or delete anywhere — yet the descriptions repeatedly direct callers to absent tools: event_create, event_set_branding, event_add_sponsor, event_submit_registration_answers, invite_join, team_post, team_assign_role, team_remove_member, company_fire_employee, account_export_data, and more. An agent following the descriptions will call nonexistent tools and fail. The read/browse coverage is very thorough, but the complete absence of the write side (which the descriptions themselves treat as existing) is a significant gap.