Skip to main content
Glama

Search jobs

waas_search

Search YC Work at a Startup jobs using structured filters for role, remote, visa, equity, salary, and more. Get relevant listings quickly.

Instructions

Search YC Work at a Startup jobs with structured filters. Builds the search URL automatically. WORKFLOW (required):

  1. waas_application_quota (or waas_search weeklyQuota) — check remaining in-app applications this week (cap is 10).

  2. waas_search with structured filters (or waas_get_job from a URL the user provides).

  3. waas_get_job + waas_get_company for full context.

  4. waas_inspect_application — returns applicationType, fields[], weeklyQuota, applyBlocked.

  5. If applicationType=weekly_limit_reached or applyBlocked=true → stop; do NOT submit.

  6. If applicationType=external → report link/email to user; do NOT auto-submit.

  7. If applicationType=needs_login → tell user to run npm run login.

  8. Draft answers for every required field in fields[].

  9. waas_submit_application with dry_run=true — show the user all answers.

  10. Only after explicit approval → dry_run=false. Never auto-submit. Skip already_applied jobs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
roleNoRole category filter.
limitNoMax results (default 30).
queryNoKeyword search.
remoteNotrue = remote only, false = on-site only.
sort_byNo
us_visaNo
job_typeNo
has_equityNo
has_salaryNo
Install Server

TDQS

B3/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose side effects and safety. It only mentions that the tool 'Builds the search URL automatically' and is a search operation, implicitly non-mutating, but does not state whether it modifies state, has rate limits, or what it returns. The 'Never auto-submit' instruction is about the agent's workflow, not the tool's behavior, so it does not clarify search behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening two sentences are concise and front-loaded. However, the description then appends a 10-step workflow that spans multiple sibling tools, making the definition overly long and diluting focus on the search tool itself. The workflow could be a separate reference; embedding it in this tool's description is not concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters (5 undocumented), no output schema, and no return-format description, the agent lacks critical context for invoking the tool correctly. The workflow mentions later steps (waas_get_job + waas_get_company) but does not describe what waas_search actually returns, how results are paginated, or how to handle ambiguous enums. This is incomplete for a structured search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers only 44% of parameters with descriptions (4 of 9). The description adds no meaning for sort_by, us_visa, job_type, has_equity, or has_salary. It merely refers to 'structured filters' generically. It even introduces 'weeklyQuota' which is not in the schema, adding confusion rather than compensating for the parameter coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence clearly states the tool's function: 'Search YC Work at a Startup jobs with structured filters.' It also adds a distinct behavioral note ('Builds the search URL automatically'). Step 2 contrasts it with waas_get_job, helping differentiate it from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Step 2 provides a conditional alternative: use waas_search with structured filters, or waas_get_job if the user supplies a URL. The workflow also instructs to skip already_applied jobs. However, the guideline is embedded in a multi-step workflow rather than stated as a crisp when-to-use rule, and there is no explicit 'do not use' condition.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Thespaceblade/waas-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server