Outreach Desk

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

The annotations already declare read-only, idempotent, non-destructive behavior, and the description adds important context: evaluations expire after 30 days, error meanings, decline feedback handling, and that the result is a draft only that is never sent. It also states the desk is the signed-in user's, so no desk_key is needed.

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?

It is front-loaded with the core purpose and then adds only operational rules: prerequisites, error recovery, defaults, decline handling, safety boundary, and authentication. Despite being several sentences, each one carries useful information.

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?

Given the existing output schema and annotations, the description covers everything needed for correct invocation: required input provenance, expiry, error recovery, decision defaults, decline-specific behavior, no-send semantics, and identity constraints.

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%, so the baseline is 3. The description still adds meaning by mapping the decision values to interested, salary/remote request, and decline, and by instructing the agent to ask the user about the feedback card for declines.

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?

It states a specific verb and resource, 'draft a reply to a scored pitch,' and enumerates the three reply types. It also distinguishes drafting from sending, which separates it from submission-oriented siblings.

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?

It gives an explicit trigger, required evaluation_id source, expiry, and concrete error recovery paths for unknown_evaluation and no_desk. It also clarifies default decision behavior and the decline feedback confirmation step.

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

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the tool is pollable (pending until a reply arrives, then answered) and carries an explicit trust boundary warning that reply content is data, not instructions — a meaningful prompt-injection disclosure.

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?

Three tight sentences: purpose first, then polling behavior, then the trust caveat. Every sentence carries distinct information and nothing is padded.

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 single-parameter read tool with an output schema and full annotation coverage, nothing an agent needs is missing. The polling semantics and the injection warning go beyond what structured fields provide, closing the remaining gaps an agent would otherwise have to discover by trial.

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?

Only one parameter exists and the schema already documents it fully (coverage 100%, including the ^fb_[0-9a-f]{32}$ pattern and the note that submit_feedback returned it), so the baseline of 3 applies. The description repeats the ticket-id linkage but adds no format or validation detail beyond the schema.

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 (Read) and resource (maintainers' reply to feedback), and ties it causally to the sibling tool submit_feedback via the ticket id. An agent can distinguish it from submit_feedback, screen_token, and wallet_identity without opening any schema.

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?

Clearly establishes the precondition: this is used after submit_feedback, with the ticket id that call returned. It does not state any exclusions or alternative ways to retrieve feedback status, but the usage context is unambiguous.

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

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

Goes well beyond the readOnly/idempotent annotations: it discloses the returned fields (volume, average scores, yield rate, recommendation), the 30-day retention window that prunes older evaluations, the 'no desk_key needed' rule, and specific remediation for no_desk and no_user_id errors.

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?

Front-loads purpose and return shape, then usage, then errors. The OAuth error-remediation sentence is long but operationally necessary; overall dense with little waste.

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?

An output schema exists, yet the description still summarizes the row shape. With auth, error paths, retention, and scoping all covered, an agent can call this correctly with little left to infer.

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% and already documents sender_domain including the 'omit for all' behavior, so the description's restatement adds little. The stripe.com example is already in the schema.

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: showing which sender domains send the best pitches, one row per domain. This is clearly distinct from score_message and the other siblings.

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?

Explicitly says to pass sender_domain for one sender and no arguments for all, routes to set_criteria when no_desk is returned, and tells the agent to ask the user to paste a pitch for score_message when nothing is scored yet.

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

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine behavior beyond that: results are ranked best-match-first and the empty-input case enumerates every tool. It says nothing about result limits or pagination, which keeps it off a 5.

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?

Four short sentences, front-loaded with what the tool does and what it returns before the usage hint. Nothing is redundant given the description is the only place ranking and empty-input behavior are stated in prose.

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 discovery tool with an output schema and full annotation coverage, this covers purpose, inputs, ranking, return fields and the no-argument case. An agent has everything needed to decide to call it and to interpret the results.

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% and the schema already explains that task, query and keyword are searched together and that omitting all lists everything. The description's 'task or keyword' phrasing actually omits 'query', so it adds no meaning beyond the schema and is marginally less complete than it.

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 ('Search the tools on this server') and adds the matching mode ('by task or keyword in plain words'). It also names what comes back (name, title, one-line summary, input fields), so an agent knows exactly what this tool produces versus the sibling action tools.

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?

'Use it when you are not sure which tool here fits a task' gives a clear triggering condition, and 'With no words it lists every tool' covers the degenerate case. It does not state when *not* to use it or name an alternative, but no sibling here offers overlapping discovery functionality, so the gap is minor.

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

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

Goes well beyond the annotations by disclosing state-dependent returns (status 'ready' with an empty form vs status 'ok' with evaluation plus three reply drafts) and the critical side effect that the evaluation is only persisted when the user has a desk — otherwise it scores against a sample profile and the agent must say so and offer set_criteria. That is exactly the kind of consequence disclosure the annotations (readOnlyHint=false only) do not provide.

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?

Five tight sentences, front-loaded with the routing decision before the return-value and side-effect details. Each sentence carries distinct operational information with no filler.

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 5-param, mutating, state-dependent tool with nested file input, the description covers selection, both return modes, the persistence caveat, and the required user-facing follow-up. Even though an output schema exists, the extra context about the sample-profile fallback is what an agent needs to act 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 description coverage is 100%, so the schema already documents sender, channel, message, priority, and the file object including the 'Do not fill it yourself' note. The description reinforces that omitting message yields the empty form and that file input comes from an attachment, but adds no format or syntax detail beyond the schema — baseline 3 applies.

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 function — the entry point for message intake that either opens the empty form or ingests an attached pitch file — and explicitly separates it from score_message for pasted pitches. An agent can pick between the two 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.

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

Gives an explicit when-to-use ('only as the entry point... or when the user attaches a pitch file'), a when-not-to-use ('For a pitch pasted in chat, use score_message instead'), and an invocation constraint ('send no desk_key'). Nothing about selection is left to inference.

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

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

Annotations already flag destructiveHint=true, but the description goes well beyond them: deletion is immediate and irreversible, the exact per-scope blast radius is listed, the success payload ('returns purged true and what was deleted') is described, the invalid_input failure path for scope sender without sender_domain is documented, and it notes the desk is implicitly the signed-in user's. This is a materially richer behavioral picture than the annotations alone.

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?

Front-loaded with purpose, then scopes, then the irreversibility warning, then return shape, then error path, then the sibling exclusion — a logical ordering. It is dense but nearly every clause carries distinct information; the error-handling sentence is the only part that could arguably live in the schema.

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?

An output schema exists, yet the description still previews the return shape in one clause, and it covers safety, per-scope semantics, prerequisites, and the alternative tool. For a two-parameter destructive tool, nothing an agent needs before invoking is missing.

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% and the schema already documents both params, including that sender_domain is required when scope is 'sender' and ignored otherwise. The description restates that relationship with a concrete example and adds the 'send no desk_key' note, which is a useful guard against an invented parameter, but on balance the schema does the heavy lifting.

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 ('permanently delete stored data') and then enumerates precisely what each scope removes: per-sender evaluations plus the scoreboard row, versus criteria, senders and evaluations for the desk. An agent can distinguish this from set_criteria and from any read siblings without opening the schema.

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?

Gives explicit when-to-use guidance per scope plus an explicit exclusion: 'Not for changing criteria; use set_criteria.' It also imposes the prerequisite 'confirm the scope with the user before calling,' which is exactly the kind of decision guidance an agent needs before a destructive call.

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

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

Annotations only declare the generic safety profile, but the description discloses real behavior: criteria override saved desk criteria and are not persisted, a cleaned summary is written to the sender scoreboard while raw text is never stored, and criteria becomes mandatory for clients with no user id. This is well beyond what annotations provide.

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?

Front-loaded with the routing decision and packed with useful detail, but the criteria persistence rule is stated twice ('they win over saved criteria and are not saved' then 'nothing is stored') and the error sentences re-state no_user_id. Slight redundancy in an otherwise dense block.

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?

An output schema exists, yet the description still summarizes the return shape (evaluation_id, composite, four sub-scores, flags, reasons, action), and it covers auth-less clients, defaults, and error codes. Nothing needed to call this correctly is missing.

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% so the baseline is 3, but the description adds routing semantics the schema cannot: send the whole pitch as message, sender_domain as a bare host or not at all, and that criteria 'wins over' saved criteria. It adds genuine value above the structured fields.

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 opening sentence names the specific action (score a pasted recruiter pitch) and immediately distinguishes it from the sibling intake_message ('form and files only'). An agent can route between the two 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.

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

Explicit when-to-use (any pitch pasted in chat), when-not (intake_message's form/file path), and the follow-on alternatives: set_criteria to persist criteria, draft_response taking the evaluation_id. Error recovery paths (no_desk, no_user_id) are spelled out too.

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

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

Annotations flag destructiveHint=true and non-idempotent, and the description goes well beyond them by naming exactly what is destroyed ('each call overwrites all saved criteria, and the earlier ones are lost'), what survives ('past evaluations and the scoreboard are kept'), and the degraded path when no user id is supplied (status not_saved, nothing stored, criteria routed to score_message). That is genuine behavioral disclosure rather than a restatement of annotations.

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?

Every sentence carries load – overwrite semantics, use cases, input tips, return values, and the no-user-id branch – and the destructive behavior is front-loaded in the first clause. It is dense and slightly run-on in the middle 'Input tips' stretch, which keeps it just short of a 5.

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 five-parameter mutation tool with an output schema, the description covers the full call lifecycle: preconditions (ask for missing required fields), destructive effect, return shape (status saved, cleaned criteria, retention note), and the failure branch. Nothing an agent needs to invoke it correctly is missing.

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%, so the schema already documents each field and its bounds, establishing a baseline of 3. The description adds real operational meaning on top: salary_floor is in whole US dollars, dealbreakers are optional, and crucially 'to change one field, send every field again with the change', which the schema cannot express.

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 states a specific verb+resource pair ('save the user's job search criteria') and immediately scopes it with the overwrite behavior. It explicitly names the sibling it is not ('Not for scoring a pitch; use score_message'), so an agent can route correctly 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.

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

It gives explicit when-to-use conditions (first setup to start the private desk, or a change of role, skills, salary floor or remote policy) and an explicit exclusion with the alternative tool named. It also prescribes a workflow step: 'Ask the user for any missing required field before calling.'

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

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

Adds substantial context beyond the annotations: it returns a ticket id, feedback is explicitly not a chat and nothing in it is executed, and links/emails/phone numbers are stripped with nothing stored about the caller. That privacy and no-execution disclosure is genuinely useful given openWorldHint=true and readOnlyHint=false.

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?

Front-loads what the tool sends, then what to pass, then what it returns, in three dense sentences with no filler. Every clause carries actionable information.

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?

Covers purpose, the enumerated kinds, the optional tool/error inputs, the 1000-character bound, the return value (ticket id), and privacy handling. With an output schema present, nothing further is required for an agent to call 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 description coverage is 100%, so the schema already documents all four parameters including the kind enum. The description restates the message length limit and the optionality of tool/error ('if you know them') but adds no syntax or format detail beyond the schema, making the baseline 3 correct.

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 ('Send feedback, a bug report or a tool request to the maintainers of the tools on this server') and enumerates the concrete situations (missing tool, stale data, broken/wrong answer). It is clearly distinguishable from the read-side sibling get_feedback_reply.

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?

Gives clear triggering conditions for each kind (need_tool, need_data, bug, other) and tells the agent to include the tool name and error text when known. It does not explicitly name the alternative get_feedback_reply or state when NOT to use this tool, so it falls short of full routing guidance.

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