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

Annotations already declare read-only, idempotent, open-world and non-destructive; the description goes well beyond them by disclosing the exact execution path (sudo -n <app>-deploy --log <lines> over the user's own SSH), the fact that the log is root-only and reachable through a single sudo rule, the host-allowlist constraint via PLESK_DEPLOY_SSH_HOSTS, and secret redaction. It also flags untrusted-content risk, which is material for a tool returning server text.

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?

Dense but front-loaded: the operation, its mechanism and its scope come first, then safety context, then the usage trigger. Every sentence carries information, though the paragraph would scan faster as short clauses and the injection warning, while relevant, adds a fifth idea to a single 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, so return values need no explanation, and the auth/permission story plus redaction are covered. Minor gap: nothing says what happens when the log is shorter than `lines`, when the host alias is not allowlisted, or whether the sudo call can fail in a way the agent should surface.

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 each of the three parameters is already documented in-schema (app naming, host alias allowlist, lines default/max). The description reinforces the host allowlist and the app naming convention but adds no new meaning such as log-format or truncation behavior for `lines`, so the 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 verb and resource — returns the last lines of the release manager's deploy log — and pins down scope precisely (last N lines, per host/app). An agent can distinguish this from deploy_status or github_deploy_runs 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?

Explicit when-to-use: when a deploy or rollback failed, to read what the release manager did. That covers the primary trigger, but no sibling alternative is named (e.g. deploy_status for current state vs. this tool for historical log text) and no explicit when-not case is given.

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 the execution path (the user's own ssh), the allowlist constraint (host must be in PLESK_DEPLOY_SSH_HOSTS), that no sudo is required, the ordering of results, and a prompt-injection warning about server/file text. These are exactly the operational facts an agent needs and that readOnlyHint/idempotentHint cannot convey.

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 action and return shape, then usage scenarios, then the safety caveat. Every clause carries 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?

A read-only inspection tool with an output schema, two fully described parameters, and rich annotations — the description still covers transport, privilege level, result ordering, and untrusted-content handling. Nothing needed 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% and both parameters are already fully documented, including the pattern and the PLESK_DEPLOY_SSH_HOSTS constraint. The description restates the ssh/allowlist context rather than adding new semantics such as alias resolution rules or what happens on an unknown alias, so the 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 concrete verb and mechanism: runs `<app>-deploy --status` over the user's ssh, and names the exact return shape (releases newest first, commits, live release, failed releases). This is clearly distinguishable from siblings like deploy_logs and rollback.

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: inspecting current deployment, before a rollback to show which release would become live, and after a rollback to confirm. It does not explicitly exclude the closest alternative (deploy_logs), so the routing is clear but not fully disambiguated.

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?

Although the annotations already flag destructiveHint=true, the description adds substantial context beyond them: dry run by default, repo-root confinement, no symlinks, no deletions, overwrite gating, FILL IN handling, and refusal to write secret-like content. These are precisely the behavioral details an agent needs before invoking a write-capable generator.

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 dense but front-loaded: purpose and default behavior come first, followed by write safety and usage sequencing. The file list is long but directly relevant to what the tool generates, and no sentence is merely repetitive.

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 complex 37-parameter generator with an output schema and destructive annotations, the description covers purpose, default dry-run behavior, write boundaries, error handling, secret refusal, and usage timing. An agent has enough context to call it correctly without needing return-value details that the output schema supplies.

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 89%, so the schema already documents most of the 37 parameters. The description adds useful meaning about unknown values becoming FILL IN and overwrite needing prior user agreement, but it does not explain most individual parameters beyond what the schema already provides.

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 and resource: it renders the deploy kit for a project. It enumerates the generated artifacts and makes clear this tool generates files, while sibling validate_deploy_kit validates them.

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 explicitly places the tool in phase 5, after the plan is agreed, and says to write only after the user has seen the diff. The default dry-run behavior and the write-only-after-diff sequence give clear when-to-use and when-not-to-use guidance.

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: states it never approves, re-runs or cancels anything, discloses that private repos are accessed via the read-only PLESK_DEPLOY_GITHUB_TOKEN and that it will never request a token from the user. It also warns that content from files and servers is data only, guarding against prompt injection.

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 the read scope, then the safety and token facts, then usage and the verification caveat. Dense but purposeful; slightly packed with semicolon-joined clauses that could be split for scanability.

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, so return-shape explanation is bonus rather than obligation, and authentication for private repos, mutation safety, and usage verification are all addressed. Nothing an agent needs to call this correctly against a 5-parameter schema 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 60%, and the description only implicitly touches parameters by calling out the 'Deploy to Plesk' workflow and the jobs. It adds no meaning for repo, limit, branch, or include_jobs beyond what the schema already documents, leaving part of the coverage gap unfilled.

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?

Names a specific verb and resource ('Reads the recent runs of the "Deploy to Plesk" workflow from the GitHub API') and enumerates the returned data (status, conclusion, commit, branch, link, approval state, jobs). It does not explicitly contrast itself with siblings like deploy_status or deploy_logs, so the agent must infer the GitHub-side vs server-side split.

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 a concrete use case ('follow a deploy the user started and to see which job failed') and an important caveat that a green run does not prove the site works, directing verification of the live URL. It stops short of naming when to pick a sibling tool instead, so exclusions are implied rather than stated.

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/non-destructive, but the description adds real value beyond them: the verified-vs-unknown fact model with file provenance, the split of env var NAMES into build-time and run-time, and the explicit guarantee that .env files are reported present but never opened. 'Changes nothing' duplicates readOnlyHint, but the privacy and output-shape disclosure is substantive.

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 front-loaded sentences with the file-type enumeration placed inline rather than as a separate list, and the sequencing instruction comes last where it is easy to find. The parenthetical inventory of manifests, lockfiles, CI workflows, etc. is dense but each item clarifies inspection scope.

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 read-only inspection tool with one optional parameter and a declared output schema, the description covers scope, result structure, privacy behavior, and workflow position. Nothing an agent needs in order to call 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% and the single parameter already documents the absolute-path form and the default to the open project, so the description adds little beyond it. Baseline 3 applies since the schema carries the parameter burden.

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?

Names a specific verb and resource ('Reads a project folder on this machine') and enumerates exactly what it inspects and returns (facts table, deployable apps, env var names). This is clearly distinguishable from the generate/validate/deploy siblings, which mutate or act on a kit rather than reading facts.

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 ordering guidance — 'Use it first, in phase 1 of setting up a Plesk deployment' — which tells the agent when to reach for it relative to the rest of the workflow. It stops short of naming which sibling to call next or stating when not to use it.

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 destructiveHint=true, idempotentHint=false, and openWorldHint=true, and the description adds substantial context beyond them: migrations are NOT undone, the release manager swaps `current`, reloads processes and checks health, and a rollback exceeding timeout_seconds keeps running server-side rather than being interrupted. It also discloses the SSH host-alias allowlist constraint and includes a prompt-injection warning about server/file text.

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 the DESTRUCTIVE marker and the mechanism before the guardrails, and each sentence carries operational information. It is dense and somewhat long, but nothing is clearly redundant for a destructive remote operation.

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 destructive, open-world mutation with an output schema present, the definition covers mechanism, confirmation gate, non-reversible side effects (migrations), and post-timeout recovery path via deploy_status. Nothing an agent needs in order to call it safely 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 75%, so most parameters are documented structurally; the description still adds value by spelling out the exact confirm token format and the semantics of timeout_seconds (the process outlives the timeout instead of aborting). The host_alias allowlist and app naming convention are largely mirrored from the schema descriptions rather than extended.

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 ('makes the previous good release live again on the server') and names the exact mechanism (`sudo -n <app>-deploy --rollback` over SSH). It is clearly distinguishable from siblings like deploy_status and deploy_logs, which the description references by name.

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 preconditions ('Call it only after the user explicitly confirms') and an ordering instruction ('Show them deploy_status first, so they know which release becomes live'). It also states the hard gate: 'confirm must be exactly "<app>@<host_alias>", or nothing runs.'

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?

Well beyond the annotations, the description discloses the fixed command set, secret redaction, that env files are listed by name only, that sudo requires password-less sudo or some commands may be denied, and that command output must be treated as data. Annotations already cover readOnly/idempotent/destructive, so this is bonus context. It doesn't say anything about runtime, output volume, or partial-failure behavior, 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?

Front-loaded with what it does, then scope, then the phase/consent guidance, then sudo semantics, then the injection caveat — a sensible ordering with almost no filler. The sudo clause is a deep parenthetical that interrupts the flow, and the closing safety sentence could be tighter, but nothing is genuinely redundant.

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?

Nine parameters, an output schema, and full annotation coverage mean the description's remaining obligations are scope, consent, and safety, all of which are stated. Combined with the note that it cannot execute arbitrary commands and that output is redacted, an agent has everything needed to invoke it safely and 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 coverage is 100%, so the baseline is 3, but the description adds real meaning for sudo ("only if that account has password-less sudo; otherwise they run as the alias's user and some may be denied") that the schema's terse "Run the commands as root with sudo -n" does not convey. The sections parameter and its default when omitted are not discussed, so it isn't a 5.

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?

"Runs the fixed, read-only discovery commands ... on the Plesk server over the user's own ssh" gives a specific verb, a bounded scope ("fixed", "It can't run any other command"), and the transport. It explicitly distinguishes itself from the sibling server_discovery_commands, which only lists those commands, so an agent can route correctly without opening a 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?

"Use it in phase 2, after the user agrees, instead of asking them to paste the output" states the timing, the precondition (user consent), and the alternative it replaces. The only mild gap is that it doesn't say when to prefer the sibling lister over this one, but the purpose sentence already implies that split.

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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the description's 'It runs nothing and connects to nothing' reinforces rather than carries the safety profile. It does add real behavioral context beyond the annotations: output is names-of-env-files only (never values), unknown values remain as <placeholders>, and the human must run the commands as root and paste results back — a non-obvious two-party interaction. It stops short of saying what the placeholders block or what happens if the user pastes partial output.

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 purpose and the alternative-tool routing are front-loaded, and no sentence is filler. However, the middle is one long comma-chained enumeration of return content that duplicates what the output schema already declares, which lengthens the definition without adding decision-relevant 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?

For a six-parameter read-only tool with full schema descriptions, complete annotations and an output schema, this is close to sufficient: it covers purpose, safety, placeholder behavior, and the hand-off to server_discover. The remaining gap is procedural — it does not say what the agent should do with the pasted-back output or that phase 2 feeds server_discover.

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 all six parameters, and the baseline is 3. The description earns above that by explaining the semantics of the five optional parameters as a group: known values are filled in and unknown ones stay as <placeholders>, which tells the agent it can call with only the required domain and still get useful output.

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: it returns a block of read-only commands for the user to run as root on the Plesk server and paste back, tagged as phase 2. The enumeration of what the block covers (Plesk/OS, PM2, systemd, ports, nginx, docroot, git status, env file names, databases, crontabs, exposure checks) makes it unmistakable against siblings like server_discover or deploy_logs.

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 triggering condition ('when you can't reach the server yourself') and an explicit ordering rule relative to a named sibling ('or before server_discover'). The agent knows both when to choose this tool and where it sits in the workflow without opening any other definition.

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/non-destructive, yet the description still adds substantial behavior: everything happens inside a temporary folder, mutations to the project are avoided, secrets are reported by file and line but never by value, and pm2/node/network are stubbed during tests. That is real context an agent could not infer from the hints.

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 core action and scoping constraint, and nearly every clause adds a distinct fact. The fourth sentence is long and list-heavy, which slightly hurts scannability, but no sentence is 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?

An output schema exists, so return values needn't be explained; the description instead covers isolation, what is checked, and how secrets are handled. For a read-only validator with three optional parameters, that is everything an agent needs before calling it.

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 all three parameters are already documented in the schema, making a baseline 3 appropriate. The description only tangentially adds meaning, noting the release-manager suite runs against the project's own copy with stand-ins, which lightly contextualizes run_release_manager_tests but gives no new syntax or defaults.

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 ("Checks the deploy kit in a project") and immediately names the exact artifacts inspected (deploy/plesk/ and .github/workflows/deploy-plesk.yml). The enumeration of checks (bash -n, shellcheck, YAML parse, safety settings, secret scan) makes it unmistakable next to siblings like generate_deploy_kit or deploy_status.

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 timing guidance: "Use it after generate_deploy_kit writes the kit, and after any change to it," which ties it to a specific sibling and workflow stage. It lacks an explicit when-not statement (e.g. don't use on a repo without a kit), so it falls just short of a 5.

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