Skip to main content
Glama

delete_mission

DestructiveIdempotent

Hard-delete a mission from the queue — silent cleanup only.

Use this only when you want to clear the row without teaching the system
anything: duplicates, accidental scrapes, leads the operator doesn't
want surfaced again but doesn't have an opinion on.

Canonical case: the post is gone by the time you get there — deleted
by the poster, 404'd, removed by mods, or stale beyond your reply
window. The lead wasn't wrong, the opportunity just evaporated.
`delete_mission` is the right tool because there's nothing to learn
from the station — its `rl_weight` stays untouched. Using
`reject_mission` here would unfairly penalise a station for an event
it didn't cause.

When to use this vs `reject_mission`:
    - `delete_mission`: queue cleanup, no learning. The scoring weight
      for the source feed is untouched. Canonical uses: post deleted,
      duplicates, accidental scrapes.
    - `reject_mission`: the lead was a bad signal and you want the
      system to learn from it. Always prefer this when you have any
      opinion on WHY the lead was wrong — the RL loop can only sharpen
      if you give it the rejection reason.

Default: if a lead looks like noise but you can categorise WHY (spam,
not relevant, too vague, etc.), reach for `reject_mission` first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mission_idYesThe mission's id, from get_missions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / mission_id / description
      Added value: +"The mission's id, from get_missions."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description goes well beyond that by disclosing the critical non-obvious side effect: the source station's rl_weight is left untouched and no learning occurs, contrasted against reject_mission's penalisation. This is exactly the kind of behavioral context annotations cannot carry.

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

Conciseness4/5

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

The one-line summary and the delete-vs-reject contrast are front-loaded and every section earns its place, but the prose is longer than a single-parameter tool strictly needs and repeats the 'no learning / rl_weight untouched' point across paragraphs.

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

Completeness5/5

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

With one required parameter, full schema coverage, no output schema, and annotations covering the safety profile, the description supplies everything an agent needs: what is destroyed, that no learning side effect occurs, and how to choose it over reject_mission.

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

Parameters3/5

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

Schema description coverage is 100% and the single mission_id parameter is already documented as coming from get_missions. The description adds no format, syntax, or sourcing detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource ('hard-delete a mission') plus the key scope qualifier ('silent cleanup only'). It explicitly differentiates from the sibling reject_mission, so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

Provides explicit when-to-use (post deleted, duplicates, accidental scrapes), when-not (anything where you can categorise WHY), the named alternative (reject_mission), and a default tie-breaker preferring reject_mission. Textbook routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.