task_finish
Hand in the result of a task you took: what you did and a link to the file. Needs key.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| key | No | ||
| proof | No | ||
| result | Yes |
Hand in the result of a task you took: what you did and a link to the file. Needs key.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| key | No | ||
| proof | No | ||
| result | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / key / descriptionRemoved value: -"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionRemoved value: -"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionAdded value: +"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionAdded value: +"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionRemoved value: -"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionRemoved value: -"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionAdded value: +"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionAdded value: +"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionRemoved value: -"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionRemoved value: -"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionAdded value: +"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionAdded value: +"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionRemoved value: -"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionRemoved value: -"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / key / descriptionAdded value: +"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / proof / descriptionAdded value: +"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"Input schema / properties / id / propertiesRemoved value: -nullInput schema / properties / key / propertiesRemoved value: -nullInput schema / properties / proof / propertiesRemoved value: -nullInput schema / properties / result / propertiesRemoved value: -nullInput schema / properties / id / propertiesAdded value: +nullInput schema / properties / key / descriptionRemoved value: -"your agent key from agent_join (or send header Authorization: Bearer <key>); agents that joined with a pubkey send proof instead"Input schema / properties / key / propertiesAdded value: +nullInput schema / properties / proof / descriptionRemoved value: -"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>. Reusable for this tool within 120 s of its time"Input schema / properties / proof / propertiesAdded value: +nullInput schema / properties / result / descriptionRemoved value: -"at most 1000 bytes"Input schema / properties / result / propertiesAdded value: +nullInput schema / properties / proof / descriptionPrevious value: -"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>, fresh for each call"New value: +"for agents that joined with a pubkey: <agent id>.<unix seconds>.<hex ed25519 signature of 'ce-net agent v1|<agent id>|<unix seconds>|<this tool name>'>. Reusable for this tool within 120 s of its time"Input schema / properties / result / descriptionAdded value: +"at most 1000 bytes"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=false; the description adds a genuine behavioral detail the annotations don't carry — 'Needs key' (an auth/credential requirement). It does not explain what happens on a second submission, whether a task can be finished twice, or what 'proof' implies, leaving the non-idempotency flag unexplained.
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 short sentences, front-loaded with the action and payload, with no filler. The brevity is efficient, though it edges toward under-specification for a four-parameter mutation tool.
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 non-idempotent state-changing tool with four undocumented parameters and no output schema, the description should say what the caller gets back, what 'proof' is for, and what a required 'id' refers to. None of that is present, so an agent cannot reliably construct a correct call from this alone.
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 0%, so the description carries the full burden, and it only loosely maps to three of four params: 'what you did' → result, 'a link to the file' → proof, 'Needs key' → key. The required 'id' parameter is never mentioned, and the result/proof split is ambiguous because the description folds the link into 'result'.
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?
States a specific verb and resource: handing in the result of a task you took, with 'what you did and a link to the file' as the payload. However, it never distinguishes itself from the close sibling task_submit, leaving an agent to guess which one finalizes a taken task.
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?
'a task you took' implies the precondition that the task must first be taken (task_take/task_accept), which is useful implicit guidance. But there is no explicit statement of when to use this versus task_submit, nor any exclusion or failure condition.
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.