tes_job_search

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It is exceptionally transparent: it states that returning only a short excerpt (not full job-description copy), includes the live faceted-search breakdown, explains how location is resolved, radius selection, validation of contract fields, and that category labels are volatile and should be read from a prior response's facets. These are non-obvious behaviors an agent must know, clearly disclosed.

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 long but every sentence earns its place. It is front-loaded with the core purpose, then methodically explains each non-obvious aspect: return value scope, facets, location resolution, filter semantics, and the volatility of category labels. There is no fluff or repetition; structure is logical and information-dense.

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?

This is a complex 12-parameter tool with no output schema, and the description covers nearly everything an agent needs: return value shape, facet handling, filter behavior, and defaults. The only gap is that page, page_size, and sort parameters are mentioned only in the schema without description-level guidance, but these are conventional pagination/sorting parameters and not critical. Overall, the description is nearly complete for the tool's 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?

Despite 100% schema coverage, the description adds substantial meaning beyond the schema. For instance, it explains that location is free-text resolved via Tes's autocomplete with a UK default, radius_miles selects radius, contract_type/term are validated against closed label sets, position/subject/workplace are passthrough filters with volatile labels, and salary_min filters by local currency with no maximum. This is a major improvement over the bare schema descriptions.

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 purpose: 'Search Tes teaching jobs.' It specifies the resource (Tes's tes.com teaching-jobs board) and the action (search). This distinguishes it from sibling tools like tes_job_detail (which retrieves a single job) and other job-board searches. The verb and resource are specific enough for an agent to select it correctly.

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 in-depth guidance on how to use the tool—how location resolution works, radius, filter validation, and how to obtain facet values. However, it never explicitly contrasts this with alternative tools (e.g., tes_job_detail for details, tes_job_employer for employer info, or other job search tools). For a search tool among many job-board siblings, explicit when-to-use versus when-not-to-use guidance is missing, though the purpose itself implies usage.

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