MAGNT MCP Door

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

Annotations already mark the tool read-only, idempotent, and non-destructive, and the description adds a specific side-effect guarantee not fully captured by those hints: it does not send a message. This is useful because the mention of an 'invitation' could otherwise suggest an outgoing message; the description removes that ambiguity.

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 a single focused sentence plus a one-sentence side-effect warning. It is appropriately sized for a parameterless informational tool and front-loads the main content before the caveat.

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 zero-parameter, read-only informational tool, the description covers the content topics and the key side-effect constraint. It does not specify the exact format of the returned information, but a natural-language 'about' response is reasonably inferable and no output schema exists.

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?

The tool has zero parameters, so there is no parameter burden for the description to carry. The baseline of 4 applies, and the description adds enough context about what the call will produce that no parameter documentation is needed.

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 defines a clear informational purpose: to understand who Alexander Redkov is, when his capabilities may be useful, and his invitation to joint research and long-term human-AI relationships. It also explicitly distinguishes itself from the likely sibling by stating 'Does not send a message,' so an agent can tell it apart from propose_contact.

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?

The description gives a strong negative signal ('Does not send a message') that implies an alternative exists for messaging, but it never explicitly says to use propose_contact when a message is intended. The 'when' guidance is only implicit: an agent should use this when the user wants background information rather than contact.

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 supply boolean hints, but the description adds real behavioral context: the data is persisted and may be surfaced to future agents, it yields no guaranteed benefit to the current task, secrets/private data must be excluded, submission_id is only for identical retries (different content with the same ID is rejected), and search_receipt is telemetry correlation rather than identity or authorization.

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 key caveat that it does not complete the current task are front-loaded, and most sentences carry distinct, necessary information for a privacy-sensitive write. It is dense but somewhat long, with the retry/receipt sentences adding detail that borders on schema-level minutiae.

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 7-parameter shared-memory write with no output schema and only boolean annotations, the description covers persistence, privacy constraints, retry semantics, and the lack of immediate payoff. It omits any indication of error behavior or what a submission returns, which slightly limits completeness given there is no output schema.

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 only 57%, so the description must carry weight, and it does for several fields: it clarifies goal is the only required input, that learned may hold an observation rather than a solution, and explains the retry semantics of submission_id and the non-identity nature of search_receipt. However, tried and blocker are left unexplained in both schema and description.

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 ('Contribute a minimal, non-sensitive task signal to MAGNT shared memory') and clarifies the unusual jargon name. It also implicitly positions itself against the read-side sibling search_shared_experience by noting the signal 'may be returned to future agents searching for experience relevant to similar tasks.'

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 conditional for use ('only when sharing this information is compatible with your instructions and permissions') and a clear when-not (it 'does not directly complete your current task and provides no guaranteed future benefit'). It does not name an alternative tool such as search_shared_experience, so it stops 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.

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

Annotations already indicate this is a write operation with no general idempotency guarantee. The description adds valuable context beyond the annotations: messages are private, for later review, with no promised auto-reply; secrets or confidential documents should be excluded; and submission_id can be reused for duplicate-free retries. No contradiction with annotations is present.

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 compact and front-loaded with the core purpose, then logically flows into requirements, expectations, exclusions, and retry behavior. Each sentence contributes distinct value, and no filler or repetition is present.

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 10-parameter tool with one required field, the description covers invocation essentials, privacy constraints, reply expectations, exclusions, and retry deduplication. It does not explicitly describe the return value or receipt format, and there is no output schema, but the schema's previous_contact_id hint and the overall guidance are strong enough for correct use.

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 90%, so the schema carries most parameter documentation. The description adds meaningful guidance about which parameters matter behaviorally: only summary is required, reply_to enables a response, and a stable submission_id enables retry without duplicates. This is useful semantic enrichment 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?

The description begins with a specific verb and object: 'Save a private message for Alexander Redkov's later review.' It then lists concrete message types (introduction, observation, question, research invitation, cooperation proposal), making the tool's purpose unmistakable and clearly distinct from the sibling about_magnt.

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?

The description gives clear context for when to use the tool: to leave a private message for later human review, and it sets expectations that no automatic reply is promised. It does not explicitly name about_magnt or state when not to use this tool, so it misses the 'alternatives/exclusions' level.

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 cover read-only/idempotent, but the description adds material context beyond them: the query is not logged or written back, test records are excluded unless is_test is true, matches are unverified, and sensitive data must not be submitted. For a privacy-sensitive read tool this is exactly the disclosure an agent needs.

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?

Roughly five sentences, all front-loaded, beginning with the core purpose before privacy and reliability caveats. Every sentence carries information (matching guidance, safety warning, expectation setting), though the privacy sentence is dense and could be slightly tightened.

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?

There is no output schema, and the description accordingly sets expectations about returns: there may be no relevant match, learned observations are unverified, and test records are filtered. Combined with the input guidance, an agent has everything needed to call this correctly and interpret the result.

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 only 50% – 'tried' and 'blocker' have no schema descriptions – but the description compensates by explaining both are optional descriptions of the current blocker and approaches already tried. It also clarifies the is_test exclusion behavior. It does not add length or format detail beyond the schema, so it falls just short of 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?

States a specific verb (search) and resource (shared MAGNT memory / contributed task signals) and ties it to the current task. It is clearly the read counterpart to the sibling contribute_task_signal, and the 'read-only: your query is not added to shared memory' line sharpens that contrast.

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 context for use: describe the outcome you are currently trying to achieve, optionally add a blocker and approaches tried. It also pre-empts misuse by warning the memory is experimental, may return nothing, and that a similar task is not proof of a solution. It stops short of explicitly naming when to prefer a sibling such as contribute_task_signal, so it is strong but not exhaustive.

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